© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 10332
    Prev
    Next
    INDEX
    Explanations

    mentions of legal proceedings and government policies

    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
    Neuron Alignment
    Index
    Value
    % of L₁
    314
    +0.11
    0.4%
    338
    +0.10
    0.4%
    647
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    338
    +0.11
    0.21
    154
    +0.10
    0.21
    293
    +0.10
    0.20
    Negative Logits
     filib
    -0.85
     litter
    -0.81
     unborn
    -0.80
     Dunn
    -0.75
     sacrific
    -0.74
     Nicarag
    -0.74
    geries
    -0.73
     miscar
    -0.73
     Guatem
    -0.71
     miscarriage
    -0.71
    POSITIVE LOGITS
    ï¸ı
    1.39
    ï¸
    1.18
    very
    1.03
    via
    1.02
    except
    1.02
    there
    1.01
    lean
    1.01
    tre
    0.99
    ternity
    0.99
    many
    0.98
    Activations Density 1.563%

    No Known Activations