© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 4-RES-JB
    11. 14837
    Prev
    Next
    INDEX
    Explanations

    instances of the word "participation."

    oai_token-act-pair · gpt-3.5-turbo

    terms related to involvement or engagement in activities or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enegger
    -0.74
    rop
    -0.71
     Canaver
    -0.67
    entious
    -0.67
     schizophren
    -0.64
    OLOG
    -0.64
    mega
    -0.63
    1001
    -0.63
    ¯¯
    -0.63
    rup
    -0.61
    POSITIVE LOGITS
     rate
    1.01
     rates
    0.97
     Rate
    0.84
     participation
    0.83
    yip
    0.82
    Rate
    0.80
    avement
    0.77
    rates
    0.76
     Rates
    0.76
     attainment
    0.76
    Activations Density 0.029%

    No Known Activations