© 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 E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 7320
    Prev
    Next
    INDEX
    Explanations

    statements related to personal experiences, emotions, and reflections

    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
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    624
    +0.12
    0.5%
    714
    +0.12
    0.5%
    393
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    661
    +0.12
    0.09
    696
    +0.12
    0.12
    119
    +0.11
    0.11
    Negative Logits
     ãĢĮ
    -0.75
    ?).
    -0.73
     �
    -0.72
    ashington
    -0.71
     });
    -0.71
    ordes
    -0.71
     ''
    -0.70
    .).
    -0.67
    =\"
    -0.65
     respectively
    -0.65
    POSITIVE LOGITS
    %"
    1.09
    xiety
    1.02
    [/
    0.95
    ":
    0.94
    ntil
    0.93
    "
    0.92
    pherd
    0.92
    chwitz
    0.91
    usterity
    0.91
    initely
    0.90
    Activations Density 4.377%

    No Known Activations