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

    Neuronpedia

    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. 1670
    Prev
    Next
    INDEX
    Explanations

    information or knowledge-related terms and concepts

    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
    285
    +0.09
    0.6%
    739
    +0.09
    0.6%
    487
    +0.08
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    285
    +0.09
    0.05
    213
    +0.09
    0.04
    162
    +0.08
    0.04
    Negative Logits
    cffffcc
    -0.58
    EStream
    -0.54
    psey
    -0.52
    */(
    -0.50
    yrus
    -0.49
     Mehran
    -0.48
    uits
    -0.47
     Archdemon
    -0.47
    scene
    -0.47
    insula
    -0.43
    POSITIVE LOGITS
    ledge
    0.77
    lege
    0.72
    ingly
    0.69
    ledged
    0.69
    ling
    0.67
    know
    0.62
    lem
    0.62
    icit
    0.61
    lean
    0.60
    ability
    0.58
    Activations Density 0.453%

    No Known Activations