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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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 E2E Recon
    5. 6-RES_SCEFR-AJT
    6. 13851
    Prev
    Next
    INDEX
    Explanations

    phrases related to sports, particularly hockey and soccer

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-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
    393
    +0.28
    1.0%
    116
    +0.17
    0.6%
    159
    +0.16
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    159
    +0.28
    0.09
    384
    +0.17
    0.07
    504
    +0.16
    0.07
    Negative Logits
    rics
    -0.91
    aws
    -0.85
    masters
    -0.85
    acers
    -0.83
    ivas
    -0.82
    pots
    -0.81
    friend
    -0.81
    resp
    -0.81
    ashes
    -0.80
    /#
    -0.78
    POSITIVE LOGITS
     week
    1.62
     morning
    1.50
     year
    1.48
     month
    1.42
     afternoon
    1.40
     weekend
    1.34
     semester
    1.27
     evening
    1.22
     century
    1.19
     summer
    1.13
    Activations Density 1.075%

    No Known Activations