© 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
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE Local
    5. 6-RES_SCL-AJT
    6. 36541
    Prev
    Next
    INDEX
    Explanations

    keywords related to political figures and policies

    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
    81
    +0.11
    0.5%
    287
    +0.10
    0.5%
    616
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    97
    +0.11
    0.06
    739
    +0.10
    0.05
    284
    +0.10
    0.10
    Negative Logits
    ategory
    -0.84
    hement
    -0.78
    icularly
    -0.77
    heastern
    -0.71
     anx
    -0.66
     downward
    -0.65
    lying
    -0.64
    ItemImage
    -0.64
    antine
    -0.63
     downwards
    -0.62
    POSITIVE LOGITS
     Humanity
    0.92
     Gaming
    0.79
     Motion
    0.78
     Addiction
    0.78
    humans
    0.77
     Represent
    0.74
     Intervention
    0.74
     Blind
    0.73
     Aging
    0.72
     Violence
    0.71
    Activations Density 10.363%

    No Known Activations