© 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. 11583
    Prev
    Next
    INDEX
    Explanations

    references to specific locations or events, particularly related to community affairs or controversies

    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
    496
    +0.23
    0.7%
    288
    +0.18
    0.6%
    503
    +0.18
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.23
    0.12
    496
    +0.18
    0.09
    346
    +0.18
    0.06
    Negative Logits
    éĹĺ
    -1.39
    ictionary
    -1.17
    anwhile
    -1.17
    ortium
    -1.16
    PsyNetMessage
    -1.12
    eers
    -1.11
    psey
    -1.09
    ablishment
    -1.08
    ierrez
    -1.07
    xual
    -1.07
    POSITIVE LOGITS
    rod
    1.50
    assment
    1.42
    vard
    1.40
    rowing
    1.33
    riet
    1.33
    row
    1.29
    rier
    1.28
    vest
    1.22
    lot
    1.20
    mare
    1.20
    Activations Density 2.017%

    No Known Activations