© 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. 3704
    Prev
    Next
    INDEX
    Explanations

    numbers combined with specific units of measurement

    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
    +0.23
    1.1%
    314
    +0.12
    0.6%
    71
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    310
    +0.23
    0.12
    71
    +0.12
    0.03
    260
    +0.11
    0.11
    Negative Logits
    ettings
    -0.68
    medi
    -0.67
    folk
    -0.66
    Fram
    -0.65
    hammad
    -0.63
    hunt
    -0.62
    venge
    -0.62
    vati
    -0.62
    plan
    -0.61
    henko
    -0.61
    POSITIVE LOGITS
    %-
    1.09
    %
    1.08
     Minutes
    1.06
     percent
    1.04
    %"
    1.02
     Shades
    0.99
    %.
    0.98
    °
    0.96
    %;
    0.96
     minutes
    0.94
    Activations Density 9.803%

    No Known Activations