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. 4533
    Prev
    Next
    INDEX
    Explanations

    names of soccer clubs and associated terms

    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
    +0.14
    0.7%
    447
    +0.12
    0.6%
    679
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    565
    +0.14
    0.06
    45
    +0.12
    0.03
    162
    +0.10
    0.06
    Negative Logits
    \\\\\\\\\\\\\\\\
    -0.72
    CHR
    -0.67
    prus
    -0.65
    ï¸ı
    -0.64
    MY
    -0.64
    tnc
    -0.64
    cipled
    -0.63
     guiActiveUn
    -0.62
    umen
    -0.62
    ebook
    -0.61
    POSITIVE LOGITS
     States
    1.03
     Nations
    1.01
    sburg
    0.91
     Airlines
    0.90
     STATES
    0.89
     Methodist
    0.88
    States
    0.76
     Artists
    0.73
     Kingdom
    0.72
    ications
    0.70
    Activations Density 7.550%

    No Known Activations