© 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. 8892
    Prev
    Next
    INDEX
    Explanations

    references to specific locations or time periods

    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
    393
    +0.38
    1.7%
    385
    +0.18
    0.8%
    362
    +0.16
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.38
    0.21
    385
    +0.18
    0.19
    393
    +0.16
    0.17
    Negative Logits
    orea
    -0.84
    ratom
    -0.83
    pport
    -0.78
    abi
    -0.77
    itars
    -0.73
     solves
    -0.73
     âĢº
    -0.73
    fax
    -0.73
    amsung
    -0.71
    ivas
    -0.71
    POSITIVE LOGITS
     same
    1.34
     aforementioned
    1.27
     latter
    1.22
     slightest
    1.10
     widest
    1.09
     usual
    1.06
     sheer
    1.06
    ses
    1.04
     outset
    1.03
     likes
    0.99
    Activations Density 2.551%

    No Known Activations