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. 45579
    Prev
    Next
    INDEX
    Explanations

    soccer-related terms and team names, especially focused on Manchester City

    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
    +0.24
    1.1%
    288
    +0.19
    0.8%
    232
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.24
    0.19
    659
    +0.19
    0.10
    430
    +0.11
    0.16
    Negative Logits
    OPLE
    -0.86
    verted
    -0.84
    ï¸ı
    -0.81
    PLA
    -0.80
    tnc
    -0.79
    EStreamFrame
    -0.73
    roach
    -0.73
    held
    -0.72
    cess
    -0.72
    ensed
    -0.71
    POSITIVE LOGITS
     Orchestra
    1.07
     City
    0.88
     Manor
    0.85
     Airways
    0.84
     Lumpur
    0.81
     Evening
    0.78
     Manchester
    0.72
     Asylum
    0.71
     Arena
    0.70
     Calling
    0.70
    Activations Density 6.464%

    No Known Activations