© 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. 8854
    Prev
    Next
    INDEX
    Explanations

    American-related content

    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%
    554
    +0.12
    0.5%
    283
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.15
    0.10
    326
    +0.12
    0.08
    232
    +0.11
    0.05
    Negative Logits
    ĵĺ
    -0.85
    eded
    -0.84
     targ
    -0.80
    pressed
    -0.80
    fax
    -0.78
    ŃĶ
    -0.78
    margin
    -0.77
    cember
    -0.76
    place
    -0.75
    absor
    -0.75
    POSITIVE LOGITS
    icans
    1.52
    ican
    1.46
    ICAN
    1.31
    gency
    1.25
    gdala
    1.21
    ica
    1.12
    icas
    1.06
    ilial
    1.04
    ikan
    1.01
    icity
    1.01
    Activations Density 1.048%

    No Known Activations