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 Local
    5. 6-RES_SCL-AJT
    6. 4318
    Prev
    Next
    INDEX
    Explanations

    pronouns ending with 'ou' and related words

    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
    301
    +0.13
    0.5%
    379
    +0.12
    0.5%
    657
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    201
    +0.13
    0.06
    211
    +0.12
    -0.03
    544
    +0.12
    0.04
    Negative Logits
    ãĥ¼ãĥ³
    -0.90
    alf
    -0.87
    Ö¼
    -0.86
    UTION
    -0.86
    ãĥŃ
    -0.85
    ãĤ¢ãĥ«
    -0.85
    é¾įå¥ij士
    -0.79
    女
    -0.78
    enegger
    -0.76
    70710
    -0.75
    POSITIVE LOGITS
    reth
    1.15
    lette
    1.09
    vre
    1.03
    seless
    1.01
    mi
    0.96
    ng
    0.96
    vernment
    0.96
    hou
    0.94
    ji
    0.93
    rette
    0.92
    Activations Density 8.617%

    No Known Activations