© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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 Local
    9. 6-RES_SCL-AJT
    11. 36516
    Prev
    Next
    INDEX
    Explanations

    numerical patterns or codes within text passages

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-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
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    447
    +0.17
    0.6%
    326
    +0.14
    0.5%
    639
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    462
    +0.17
    0.07
    6
    +0.14
    0.11
    434
    +0.12
    0.05
    Negative Logits
     reluct
    -0.97
    anooga
    -0.97
    querque
    -0.95
     tremend
    -0.94
    hya
    -0.90
     millenn
    -0.88
     explanatory
    -0.85
    ĸļ
    -0.81
     neighb
    -0.81
    reon
    -0.80
    POSITIVE LOGITS
    .............
    1.10
    504
    1.02
    454
    1.02
    641
    0.97
    651
    0.97
    503
    0.96
    806
    0.96
    657
    0.96
    458
    0.95
    756
    0.94
    Activations Density 10.538%

    No Known Activations