© 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. 13973
    Prev
    Next
    INDEX
    Explanations

    statements reflecting strong judgment or criticism

    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
    285
    +0.09
    0.5%
    465
    +0.08
    0.5%
    331
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    52
    +0.09
    0.08
    6
    +0.08
    0.16
    442
    +0.08
    0.08
    Negative Logits
     overnight
    -0.55
     subsistence
    -0.53
     assets
    -0.52
    ynthesis
    -0.52
     manuscripts
    -0.51
     whites
    -0.50
     plank
    -0.50
     Worlds
    -0.48
     wings
    -0.48
     dotted
    -0.47
    POSITIVE LOGITS
    ably
    1.20
    ately
    1.05
    abl
    0.92
    ful
    0.91
    lessly
    0.86
    abil
    0.85
    ously
    0.82
    able
    0.80
    FUL
    0.78
    ABLE
    0.74
    Activations Density 15.706%

    No Known Activations