© 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. 9112
    Prev
    Next
    INDEX
    Explanations

    locations and events related to Santa

    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
    421
    +0.19
    0.8%
    343
    +0.14
    0.6%
    288
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.19
    0.06
    343
    +0.14
    0.05
    421
    +0.14
    0.04
    Negative Logits
    irection
    -0.87
    ership
    -0.78
    edly
    -0.78
    hower
    -0.77
    ochond
    -0.76
    restling
    -0.76
    ives
    -0.74
    toggle
    -0.73
    orph
    -0.72
    draw
    -0.71
    POSITIVE LOGITS
     Claus
    1.81
     Clara
    1.20
     Monica
    1.14
     Ana
    1.12
     Clause
    1.12
     Barbara
    1.08
     Lumpur
    1.02
     Cruz
    1.02
     Clar
    1.00
     Rosa
    0.99
    Activations Density 0.625%

    No Known Activations