© 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. 1979
    Prev
    Next
    INDEX
    Explanations

    phrases related to making judgments or expressing opinions

    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
    •Layer 6 UMAP region: Mixed in middle - e2e-recon

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    7
    +0.19
    0.7%
    679
    +0.19
    0.7%
    386
    +0.16
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    7
    +0.19
    0.05
    288
    +0.19
    0.06
    744
    +0.16
    0.04
    Negative Logits
    href
    -1.10
    tails
    -0.95
    heny
    -0.91
    ieri
    -0.90
    atern
    -0.89
    ohyd
    -0.89
    oples
    -0.87
    ogene
    -0.87
     Founding
    -0.86
    udi
    -0.86
    POSITIVE LOGITS
     judgment
    1.52
     judgement
    1.43
     Judgment
    1.28
    eering
    1.16
     judgments
    1.15
    naire
    1.11
    ij士
    1.02
    jud
    0.97
    aries
    0.96
     debtor
    0.95
    Activations Density 0.626%

    No Known Activations