© 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. 9083
    Prev
    Next
    INDEX
    Explanations

    financial and political terms or concepts

    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
    288
    +0.15
    0.6%
    326
    +0.12
    0.5%
    373
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.15
    0.18
    709
    +0.12
    0.11
    225
    +0.12
    0.10
    Negative Logits
     oun
    -0.89
    cow
    -0.76
    mos
    -0.75
    nih
    -0.74
    paren
    -0.74
    rongh
    -0.74
    undai
    -0.73
    onde
    -0.71
    vez
    -0.71
    odd
    -0.70
    POSITIVE LOGITS
    aneously
    1.22
    iously
    1.01
     extraord
    1.00
    edly
    0.95
    theless
    0.93
    tenance
    0.90
    terday
    0.83
    ishly
    0.82
    eers
    0.78
    ically
    0.77
    Activations Density 4.007%

    No Known Activations