© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    5. GPT2-Small
    7. Residual Similar CE Local
    9. 6-RES_SCL-AJT
    11. 5051
    Prev
    Next
    INDEX
    Explanations

    words related to security and safety concerns, including physical attacks, law enforcement incidents, and geopolitical tensions

    oai_token-act-pair · gpt-3.5-turbo

    verbs in the past tense or expressions related to actions that were completed

    oai_token-act-pair · gpt-3.5-turboTriggered by @danbraun
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-ajt
    Prompts (Dashboard)
    12,288 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    46,080
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    apollo-research/Skylion007-openwebtext-tokenizer-gpt2
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    717
    +0.11
    0.5%
    393
    +0.10
    0.5%
    378
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    566
    +0.11
    0.20
    718
    +0.10
    0.24
    762
    +0.10
    0.25
    Negative Logits
     bearer
    -0.90
    AME
    -0.67
     simultane
    -0.63
     Anat
    -0.62
     Ãĸ
    -0.60
     Collective
    -0.60
     Agenda
    -0.59
    ULT
    -0.58
     Axis
    -0.57
    Drag
    -0.57
    POSITIVE LOGITS
    illard
    0.77
    lé
    0.75
    okia
    0.75
    ilater
    0.74
    dB
    0.71
    lear
    0.69
     nonetheless
    0.69
    ptin
    0.69
     anyway
    0.69
    uno
    0.68
    Activations Density 15.082%

    No Known Activations