© 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. 11203
    Prev
    Next
    INDEX
    Explanations

    mentions of crimes and legal procedures

    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: Mostly-local cluster on left - e2e-recon

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    393
    +0.20
    0.8%
    109
    +0.13
    0.5%
    616
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    29
    +0.20
    0.08
    22
    +0.13
    0.08
    235
    +0.12
    0.08
    Negative Logits
    bian
    -1.01
    asy
    -0.96
    bia
    -0.94
    velt
    -0.94
    ertain
    -0.92
    inea
    -0.91
    ministic
    -0.90
    ational
    -0.90
    idad
    -0.87
    pring
    -0.85
    POSITIVE LOGITS
     virtue
    1.48
    laws
    1.18
    gone
    1.14
    products
    1.13
    product
    0.97
     2050
    0.93
     proxy
    0.92
     multiplying
    0.88
     omission
    0.88
     Hilton
    0.86
    Activations Density 0.925%

    No Known Activations