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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 32368
    Prev
    Next
    INDEX
    Explanations

    expressions related to political comments or criticisms

    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
    +0.35
    1.7%
    393
    +0.13
    0.6%
    269
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    447
    +0.35
    0.40
    138
    +0.13
    0.37
    64
    +0.10
    -0.26
    Negative Logits
     senses
    -0.69
     ceremon
    -0.67
    agues
    -0.62
     Gain
    -0.61
    iture
    -0.61
     trades
    -0.60
     Yor
    -0.60
     whistle
    -0.58
     floats
    -0.58
    ão
    -0.58
    POSITIVE LOGITS
    Reviewer
    0.80
    KER
    0.79
    GRE
    0.79
    VALUE
    0.71
    Ĥİ
    0.70
     actually
    0.67
    rael
    0.67
    DATA
    0.67
     Solitaire
    0.66
    VAL
    0.65
    Activations Density 15.872%

    No Known Activations