© 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 Local
    9. 6-RES_SCL-AJT
    11. 34050
    Prev
    Next
    INDEX
    Explanations

    names

    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
    +0.19
    1.1%
    232
    +0.10
    0.6%
    541
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    370
    +0.19
    0.06
    139
    +0.10
    0.07
    374
    +0.10
    0.04
    Negative Logits
    20439
    -0.63
     redistributed
    -0.62
    emale
    -0.61
    ãĥ´ãĤ¡
    -0.60
    ASED
    -0.60
    ãĥĩãĤ£
    -0.57
    女
    -0.57
    velt
    -0.56
     à¨
    -0.55
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.55
    POSITIVE LOGITS
    laus
    1.05
    named
    0.91
    names
    0.85
    ety
    0.84
    olas
    0.84
    las
    0.81
    imus
    0.77
    erson
    0.75
    y
    0.73
     Fury
    0.71
    Activations Density 12.823%

    No Known Activations