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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 2673
    Prev
    Next
    INDEX
    Explanations

    instances where an action of turning something off is being described

    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
    224
    +0.10
    0.5%
    766
    +0.10
    0.5%
    717
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    273
    +0.10
    0.02
    424
    +0.10
    0.02
    471
    +0.10
    0.02
    Negative Logits
    elf
    -0.73
    ought
    -0.71
    umper
    -0.64
    formed
    -0.64
    ilage
    -0.64
    omers
    -0.63
    lation
    -0.62
    pei
    -0.62
    lished
    -0.62
    onest
    -0.59
    POSITIVE LOGITS
     regress
    0.69
    Exit
    0.64
    rection
    0.61
     residual
    0.59
    awaru
    0.59
     resist
    0.59
     electors
    0.59
    reb
    0.58
    isy
    0.57
    20439
    0.57
    Activations Density 0.042%

    No Known Activations