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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 34542
    Prev
    Next
    INDEX
    Explanations

    mathematical and geometric terms related to circles, curve curvatures, and transformations

    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%
    267
    +0.17
    0.7%
    630
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    447
    +0.28
    0.16
    138
    +0.17
    0.13
    64
    +0.13
    -0.20
    Negative Logits
    door
    -0.95
     mathemat
    -0.86
    olkien
    -0.85
    NetMessage
    -0.84
    puter
    -0.80
    urations
    -0.78
    URA
    -0.77
    reet
    -0.75
    earchers
    -0.74
    liga
    -0.73
    POSITIVE LOGITS
    ity
    1.06
    apolis
    0.95
    ism
    0.94
    ess
    0.89
    ians
    0.89
    nis
    0.88
    thus
    0.88
     Airlines
    0.84
    ova
    0.81
     Airways
    0.79
    Activations Density 10.225%

    No Known Activations