© 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. 9133
    Prev
    Next
    INDEX
    Explanations

    biographical and anecdotal information

    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
    664
    +0.14
    0.5%
    659
    +0.14
    0.5%
    128
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    767
    +0.14
    0.11
    664
    +0.14
    0.10
    332
    +0.13
    0.10
    Negative Logits
    milo
    -0.86
     precon
    -0.84
     spiked
    -0.82
     Pharaoh
    -0.80
     Presidents
    -0.79
     fet
    -0.78
     RELE
    -0.78
     buzz
    -0.78
    ISON
    -0.77
    FINE
    -0.77
    POSITIVE LOGITS
    ources
    1.91
    ourced
    1.64
    ustain
    1.52
    ued
    1.50
    arah
    1.47
    essions
    1.45
    atisf
    1.45
    atellite
    1.41
    ourcing
    1.40
    wered
    1.39
    Activations Density 1.443%

    No Known Activations