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. 4285
    Prev
    Next
    INDEX
    Explanations

    references to soccer events and competitions such as the World Cup

    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%
    146
    +0.12
    0.6%
    288
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    146
    +0.24
    0.08
    620
    +0.12
    0.03
    294
    +0.12
    0.02
    Negative Logits
    bart
    -0.77
    utenant
    -0.75
     mathemat
    -0.73
    */(
    -0.72
    ipt
    -0.69
    ogyn
    -0.68
    paio
    -0.68
    ãĤ¨ãĥ«
    -0.68
    ksh
    -0.68
    verified
    -0.68
    POSITIVE LOGITS
     Finals
    0.96
     qualifiers
    0.93
    eers
    0.85
     qualifier
    0.81
     finals
    0.80
     organised
    0.78
     Uruguay
    0.78
     Qual
    0.77
     Playoffs
    0.76
     qualifying
    0.76
    Activations Density 6.366%

    No Known Activations