© 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 EvalsExportsAPI 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. 12892
    Prev
    Next
    INDEX
    Explanations

    specific sets of characters or keywords based on a technical context, potentially related to programming or software development

    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
    269
    +0.19
    0.6%
    326
    +0.18
    0.6%
    377
    +0.15
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.19
    0.11
    288
    +0.18
    0.11
    232
    +0.15
    0.07
    Negative Logits
    代
    -1.24
     misunder
    -1.04
    DonaldTrump
    -1.01
    nces
    -1.01
    andals
    -0.97
    ÑĮ
    -0.95
    ewski
    -0.94
    iltr
    -0.94
    olson
    -0.92
     distingu
    -0.92
    POSITIVE LOGITS
    gey
    1.49
    zee
    1.47
    oos
    1.45
    edo
    1.33
    ey
    1.30
    leans
    1.30
    Commerce
    1.27
    lean
    1.27
    zing
    1.24
    eful
    1.23
    Activations Density 1.891%

    No Known Activations