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. 13359
    Prev
    Next
    INDEX
    Explanations

    information related to financial transactions or agreements

    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
    +0.50
    2.5%
    496
    +0.14
    0.7%
    481
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    338
    +0.50
    0.13
    385
    +0.14
    0.17
    602
    +0.10
    0.10
    Negative Logits
     grazing
    -0.67
    sted
    -0.65
    wcs
    -0.62
    TPPStreamerBot
    -0.60
    acan
    -0.60
    aca
    -0.59
    romeda
    -0.59
     pri
    -0.58
    aston
    -0.58
    ``
    -0.56
    POSITIVE LOGITS
     Ibid
    0.78
     Measures
    0.76
     Continued
    0.73
     Various
    0.71
     Unable
    0.69
     References
    0.69
     Historical
    0.68
     Proced
    0.68
     Secondary
    0.67
     Seek
    0.67
    Activations Density 11.052%

    No Known Activations