© 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. 8731
    Prev
    Next
    INDEX
    Explanations

    locations and items related to the zoo

    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
    288
    +0.19
    0.8%
    251
    +0.11
    0.5%
    44
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.19
    0.31
    575
    +0.11
    0.22
    270
    +0.11
    0.10
    Negative Logits
    thora
    -0.95
    cale
    -0.91
    hots
    -0.87
    hift
    -0.86
    htaking
    -0.86
    ï¸ı
    -0.85
    terday
    -0.80
    laus
    -0.78
    xit
    -0.76
     Canaver
    -0.74
    POSITIVE LOGITS
    wide
    1.35
    mates
    1.14
     mates
    1.00
    mate
    0.96
     administrator
    0.96
     manager
    0.94
    emetery
    0.91
     clerk
    0.89
    esan
    0.89
     itself
    0.84
    Activations Density 6.394%

    No Known Activations