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. 4550
    Prev
    Next
    INDEX
    Explanations

    abbreviations related to gaming and technology

    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
    578
    +0.14
    0.7%
    343
    +0.12
    0.6%
    447
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    447
    +0.14
    0.31
    138
    +0.12
    0.29
    64
    +0.12
    -0.16
    Negative Logits
     GOODMAN
    -0.85
    iatus
    -0.68
     Lauder
    -0.66
     defic
    -0.64
    ãĥ³ãĤ¸
    -0.64
    ãĤ¨ãĥ«
    -0.62
    mus
    -0.62
    gdala
    -0.61
     MacArthur
    -0.60
     aval
    -0.60
    POSITIVE LOGITS
    olicy
    0.90
    ublic
    0.80
    lyak
    0.75
    ython
    0.73
    vP
    0.71
    olitics
    0.70
    retty
    0.70
    ivot
    0.69
    FW
    0.69
    arser
    0.69
    Activations Density 6.046%

    No Known Activations