© 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. 7656
    Prev
    Next
    INDEX
    Explanations

    fan-related content, such as fan works, fan art, and interactions between fans and performers

    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
    0.6%
    63
    +0.16
    0.5%
    61
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    63
    +0.19
    0.06
    568
    +0.16
    0.05
    146
    +0.13
    0.05
    Negative Logits
     bip
    -0.85
     Territ
    -0.84
     Macro
    -0.81
     Labrador
    -0.80
     Proceedings
    -0.80
    ateral
    -0.80
     Barkley
    -0.80
    NESS
    -0.78
     Bib
    -0.77
     VIDEOS
    -0.77
    POSITIVE LOGITS
    atics
    1.70
    atical
    1.66
    club
    1.40
    boys
    1.40
    fare
    1.30
    atically
    1.29
    boy
    1.23
    hetical
    1.23
    coni
    1.19
    hetically
    1.17
    Activations Density 0.803%

    No Known Activations