© 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. 2928
    Prev
    Next
    INDEX
    Explanations

    code snippets related to programming concepts and syntax

    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
    167
    +0.18
    0.6%
    459
    +0.17
    0.6%
    552
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    441
    +0.18
    0.01
    356
    +0.17
    0.01
    448
    +0.14
    0.01
    Negative Logits
    zzi
    -1.06
    ppo
    -1.05
    edia
    -1.03
    zig
    -1.02
    ches
    -1.00
    dos
    -0.99
    ombies
    -0.99
     resil
    -0.98
    drive
    -0.98
    idem
    -0.97
    POSITIVE LOGITS
    expr
    1.62
    ipation
    1.31
    rait
    1.24
    raining
    1.22
    rast
    1.19
    abulary
    1.19
    ricting
    1.17
    ellation
    1.17
    ricted
    1.16
    rain
    1.15
    Activations Density 0.122%

    No Known Activations