© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    5. GPT2-Small
    7. Residual Similar CE Local
    9. 6-RES_SCL-AJT
    11. 12942
    Prev
    Next
    INDEX
    Explanations

    data related to programming languages and software development, specifically focusing on GNU licensing, Unix environments, code syntax, and software features

    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
    0.6%
    267
    +0.13
    0.6%
    302
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.14
    0.22
    288
    +0.13
    0.23
    578
    +0.11
    0.04
    Negative Logits
    idas
    -0.74
    ales
    -0.74
    yy
    -0.71
    bro
    -0.70
    arbon
    -0.68
    oles
    -0.67
    asin
    -0.67
    lain
    -0.67
    bell
    -0.66
    itate
    -0.66
    POSITIVE LOGITS
     Emacs
    0.73
    ãĥ¼ãĥĨãĤ£
    0.71
    URE
    0.71
    izens
    0.68
    circ
    0.66
    ãĥ¥
    0.66
    gments
    0.65
     FTP
    0.64
    Copyright
    0.64
     grep
    0.64
    Activations Density 7.084%

    No Known Activations