© 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. 13906
    Prev
    Next
    INDEX
    Explanations

    terms related to labor and working-class issues

    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
    343
    +0.09
    0.5%
    641
    +0.09
    0.5%
    496
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    343
    +0.09
    0.09
    326
    +0.09
    0.23
    428
    +0.09
    0.05
    Negative Logits
    HER
    -0.67
    apo
    -0.54
    eln
    -0.52
    olute
    -0.52
    ery
    -0.52
    ecake
    -0.51
    emaker
    -0.51
    idious
    -0.51
    heet
    -0.50
    CHR
    -0.50
    POSITIVE LOGITS
    hood
    0.84
    rowing
    0.78
    bor
    0.70
    rower
    0.70
    iculture
    0.67
    izon
    0.66
    bid
    0.61
    rows
    0.61
     Gw
    0.59
    ror
    0.59
    Activations Density 9.099%

    No Known Activations