© 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. 10606
    Prev
    Next
    INDEX
    Explanations

    references to specific characters and events in sports and entertainment, as well as technical details and acronyms

    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
    115
    +0.03
    0.5%
    404
    +0.03
    0.4%
    216
    +0.02
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.03
    0.03
    57
    +0.03
    0.02
    137
    +0.02
    0.02
    Negative Logits
    ogi
    -0.22
    earchers
    -0.20
    essen
    -0.20
    urger
    -0.20
    iel
    -0.19
    obiles
    -0.19
    oslav
    -0.19
    undo
    -0.18
    weed
    -0.18
    aughs
    -0.18
    POSITIVE LOGITS
     ç¥ŀ
    0.20
     Aether
    0.20
     Elements
    0.20
     Seraph
    0.19
     Tub
    0.18
     Til
    0.18
     Transgender
    0.17
     Tad
    0.17
     Tob
    0.17
     Chron
    0.17
    Activations Density 0.164%

    No Known Activations