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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 40370
    Prev
    Next
    INDEX
    Explanations

    arguments or sentiments emphasizing a strong stance on social or political issues

    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
    +0.28
    1.2%
    481
    +0.14
    0.6%
    393
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.28
    0.30
    362
    +0.14
    0.13
    437
    +0.12
    0.07
    Negative Logits
    ipeg
    -0.75
     Nare
    -0.71
    igm
    -0.70
    ovember
    -0.68
    WN
    -0.67
    ason
    -0.66
    Notes
    -0.66
    su
    -0.65
    uden
    -0.64
     attRot
    -0.63
    POSITIVE LOGITS
     la
    0.66
     slightest
    0.64
     clot
    0.64
    asso
    0.63
     decency
    0.60
    mone
    0.58
     hypoc
    0.58
     simultane
    0.57
     embassies
    0.57
     metre
    0.57
    Activations Density 13.452%

    No Known Activations