© 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. 13159
    Prev
    Next
    INDEX
    Explanations

    phrases related to accidents or incidents involving physical damage or injury

    oai_token-act-pair · gpt-3.5-turbo
    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
    447
    +0.22
    1.0%
    481
    +0.11
    0.5%
    683
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    41
    +0.22
    0.10
    289
    +0.11
    -0.04
    678
    +0.10
    0.08
    Negative Logits
    enne
    -0.75
    ouble
    -0.74
    umblr
    -0.69
    weet
    -0.69
    âĺħâĺħ
    -0.69
    anguage
    -0.68
    abetes
    -0.68
    rike
    -0.68
    Quantity
    -0.67
    ampunk
    -0.66
    POSITIVE LOGITS
     protr
    1.04
     separating
    0.95
     roof
    0.87
     junction
    0.86
     doors
    0.85
     connecting
    0.85
     condu
    0.84
     entrances
    0.84
     shaft
    0.84
     barrier
    0.81
    Activations Density 13.442%

    No Known Activations