© 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. 11142
    Prev
    Next
    INDEX
    Explanations

    proper nouns or specific terms related to technology, software, and other related fields

    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
    739
    +0.23
    0.7%
    575
    +0.19
    0.6%
    721
    +0.18
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.23
    0.07
    466
    +0.19
    0.05
    232
    +0.18
    0.04
    Negative Logits
    ccording
    -1.00
    anyahu
    -0.98
    ioch
    -0.94
    ibaba
    -0.91
    culosis
    -0.91
    İĭ
    -0.91
    inates
    -0.90
    paio
    -0.90
    iden
    -0.89
    pn
    -0.88
    POSITIVE LOGITS
    steen
    1.64
    trap
    1.48
    dale
    1.23
    meier
    1.16
    lings
    1.13
    field
    1.10
    Board
    1.09
    mary
    1.09
    board
    1.08
     Awakening
    1.06
    Activations Density 1.014%

    No Known Activations