© 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. 7583
    Prev
    Next
    INDEX
    Explanations

    words related to specific events or details within a larger context

    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
    699
    +0.19
    0.6%
    587
    +0.13
    0.4%
    216
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.19
    0.11
    404
    +0.13
    0.08
    699
    +0.13
    0.04
    Negative Logits
    URA
    -1.16
    EEK
    -1.10
    merce
    -1.07
    bsite
    -1.00
     Sawyer
    -1.00
    ĸļ
    -0.96
    riad
    -0.95
    urai
    -0.94
    ullivan
    -0.94
    gerald
    -0.93
    POSITIVE LOGITS
    ysis
    1.60
    tarians
    1.49
    ogy
    1.46
    arial
    1.39
    ogical
    1.38
    pha
    1.37
    tarian
    1.25
    ities
    1.25
    isks
    1.24
    ibrary
    1.18
    Activations Density 1.584%

    No Known Activations