Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 13385
    Prev
    Next
    INDEX
    Explanations

    references to current events and political figures

    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
    288
    +0.11
    0.5%
    516
    +0.11
    0.5%
    481
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.11
    0.30
    516
    +0.11
    0.13
    575
    +0.11
    0.20
    Negative Logits
    theless
    -0.91
     millenn
    -0.81
     anecd
    -0.80
     rul
    -0.80
    ngth
    -0.80
     nep
    -0.78
     âĶľ
    -0.78
     ---------
    -0.77
     pse
    -0.77
     dilig
    -0.76
    POSITIVE LOGITS
     ÂŃ
    0.79
     Donald
    0.73
    Islam
    0.72
     Belfast
    0.71
     Hillary
    0.71
     taxpayer
    0.71
     amid
    0.71
     Islamist
    0.69
    ÂŃ
    0.69
     Wednesday
    0.67
    Activations Density 12.716%

    No Known Activations