© 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. 7516
    Prev
    Next
    INDEX
    Explanations

    information related to news articles, product features, and specifications

    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
    +0.20
    0.7%
    325
    +0.12
    0.4%
    679
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    744
    +0.20
    0.03
    311
    +0.12
    0.01
    679
    +0.12
    0.03
    Negative Logits
    gren
    -0.99
    asm
    -0.98
    cffffcc
    -0.90
    unci
    -0.86
     displ
    -0.86
    oji
    -0.85
    otally
    -0.85
    gey
    -0.84
    gee
    -0.82
     violently
    -0.81
    POSITIVE LOGITS
     Highlights
    1.03
    peed
    1.01
    ï¸ı
    0.98
     VIDEOS
    0.97
     Serving
    0.95
     Timeline
    0.93
     Include
    0.93
     Archive
    0.89
     âĶľ
    0.89
     Surviv
    0.88
    Activations Density 0.223%

    No Known Activations