© 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 E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 3623
    Prev
    Next
    INDEX
    Explanations

    commands related to file manipulation and control flow structures in a programming context

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-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
    +0.16
    0.6%
    301
    +0.14
    0.5%
    25
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    176
    +0.16
    0.08
    314
    +0.14
    0.00
    326
    +0.14
    0.12
    Negative Logits
     arsen
    -0.86
     consequential
    -0.82
    Reviewer
    -0.76
     tremend
    -0.76
    Dialogue
    -0.76
     Charm
    -0.74
     Shepherd
    -0.73
     foregoing
    -0.73
     Oops
    -0.72
    ZI
    -0.72
    POSITIVE LOGITS
    theless
    1.71
    tenance
    1.67
    terday
    1.66
    etheless
    1.66
    bsite
    1.39
    bidden
    1.17
    ruction
    1.17
    llor
    1.17
    gotten
    1.11
    itage
    1.11
    Activations Density 2.374%

    No Known Activations