© 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. 46018
    Prev
    Next
    INDEX
    Explanations

    references to spare items or resources

    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
    326
    +0.13
    0.6%
    447
    +0.12
    0.5%
    709
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.13
    0.17
    636
    +0.12
    0.10
    393
    +0.10
    0.31
    Negative Logits
    anwhile
    -0.68
    ablishment
    -0.67
    essee
    -0.66
    stasy
    -0.65
    SOURCE
    -0.65
    uador
    -0.64
    rus
    -0.64
     appropri
    -0.64
    iggurat
    -0.64
    roots
    -0.64
    POSITIVE LOGITS
     spare
    0.84
     tire
    0.80
    liest
    0.73
    ricular
    0.69
     spared
    0.68
    zzi
    0.67
    plane
    0.66
    ware
    0.65
     vent
    0.64
     beds
    0.63
    Activations Density 15.153%

    No Known Activations