© 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
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE Local
    5. 6-RES_SCL-AJT
    6. 4828
    Prev
    Next
    INDEX
    Explanations

    technical terms and content related to biology and genetics

    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
    554
    +0.11
    0.6%
    437
    +0.10
    0.5%
    551
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.11
    0.27
    326
    +0.10
    0.23
    709
    +0.09
    0.14
    Negative Logits
    ignt
    -0.66
    gent
    -0.65
    teen
    -0.62
     cleaner
    -0.60
    uates
    -0.58
    pas
    -0.58
     Hurricanes
    -0.58
    ilies
    -0.55
    fighters
    -0.54
     Tempest
    -0.53
    POSITIVE LOGITS
    ĸļ
    0.69
    lique
    0.67
    riad
    0.66
    ITED
    0.65
    ERC
    0.64
    SourceFile
    0.64
    rade
    0.63
    ļéĨĴ
    0.62
    oda
    0.61
    wana
    0.61
    Activations Density 7.753%

    No Known Activations