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. 40269
    Prev
    Next
    INDEX
    Explanations

    instructions for preparing food

    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
    681
    +0.05
    0.4%
    575
    +0.05
    0.4%
    91
    +0.05
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    575
    +0.05
    0.25
    288
    +0.05
    0.32
    270
    +0.05
    0.08
    Negative Logits
    amily
    -0.38
    nces
    -0.37
    eq
    -0.36
    phas
    -0.35
    atism
    -0.35
     Sons
    -0.35
    ajor
    -0.35
    anchester
    -0.34
    faith
    -0.33
    missing
    -0.32
    POSITIVE LOGITS
     or
    0.55
     etc
    0.50
    .''.
    0.44
    )).
    0.43
    ®,
    0.38
    .�
    0.36
    entary
    0.36
     tray
    0.35
     unnoticed
    0.35
    .ãĢį
    0.35
    Activations Density 15.702%

    No Known Activations