© 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
    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. 35102
    Prev
    Next
    INDEX
    Explanations

    keywords related to computer programming, such as language names, code snippets, API calls, and variable names

    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
    213
    +0.13
    0.6%
    739
    +0.11
    0.5%
    447
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    239
    +0.13
    0.06
    213
    +0.11
    0.05
    749
    +0.10
    0.05
    Negative Logits
    owship
    -0.74
    strous
    -0.74
    inen
    -0.73
    ataka
    -0.73
    iversal
    -0.73
    igious
    -0.68
    auder
    -0.68
    ihara
    -0.67
    ieties
    -0.67
    zee
    -0.66
    POSITIVE LOGITS
    code
    0.74
    otle
    0.72
     snippet
    0.70
    Code
    0.63
    mable
    0.63
    codes
    0.62
     coded
    0.59
    IME
    0.58
     Reduction
    0.58
    Pen
    0.57
    Activations Density 3.044%

    No Known Activations