© 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
    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. 13896
    Prev
    Next
    INDEX
    Explanations

    historical events, political actions, and societal issues related to government 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
    447
    +0.21
    0.9%
    481
    +0.14
    0.6%
    715
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    222
    +0.21
    0.07
    199
    +0.14
    0.16
    288
    +0.12
    0.25
    Negative Logits
     Frie
    -0.71
    Ö¼
    -0.70
    sheets
    -0.68
     Compare
    -0.67
    rote
    -0.66
     anecd
    -0.65
     STD
    -0.63
     fractions
    -0.63
    ãĥ¼ãĥĨãĤ£
    -0.62
     smelled
    -0.62
    POSITIVE LOGITS
    xit
    1.09
    determination
    1.03
    ependence
    1.00
     unification
    0.93
     independence
    0.92
    inition
    0.90
     restoration
    0.89
     continuation
    0.85
    ilee
    0.85
     separation
    0.84
    Activations Density 16.353%

    No Known Activations