© 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. 40691
    Prev
    Next
    INDEX
    Explanations

    mentions of threats to security, safety, or stability in different contexts

    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
    +0.15
    1.0%
    329
    +0.07
    0.4%
    549
    +0.07
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.15
    0.35
    640
    +0.07
    0.30
    608
    +0.07
    0.23
    Negative Logits
     Bought
    -0.54
    eret
    -0.52
    soDeliveryDate
    -0.51
    displayText
    -0.48
     Edited
    -0.47
     dances
    -0.46
     calculates
    -0.46
     approves
    -0.45
    ahon
    -0.45
     danced
    -0.45
    POSITIVE LOGITS
     retaliation
    0.62
     endanger
    0.59
     retribution
    0.58
    ailability
    0.56
     repr
    0.55
     livelihood
    0.53
     jeopard
    0.52
     extinction
    0.52
     harming
    0.52
     trespass
    0.51
    Activations Density 16.495%

    No Known Activations