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. 4344
    Prev
    Next
    INDEX
    Explanations

    specific references to years or time periods

    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
    +0.31
    1.4%
    459
    +0.12
    0.6%
    279
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    279
    +0.31
    0.12
    173
    +0.12
    0.08
    452
    +0.10
    0.07
    Negative Logits
    UTF
    -0.70
    mel
    -0.65
    utf
    -0.63
     sqor
    -0.60
    SOURCE
    -0.60
    rice
    -0.60
    Comments
    -0.58
    ]+
    -0.58
    azeera
    -0.58
    urat
    -0.57
    POSITIVE LOGITS
    eve
    0.72
    cific
    0.66
     onwards
    0.64
     however
    0.64
     marked
    0.63
     Tonight
    0.61
     edition
    0.60
     marks
    0.59
    days
    0.59
    ãĤ·ãĥ£
    0.58
    Activations Density 10.157%

    No Known Activations