© 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. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 8-RES-JB
    11. 14885
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to participation or involvement

    oai_token-act-pair · gpt-3.5-turbo

    the act of participating in various activities or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cale
    -0.78
    pex
    -0.75
    forward
    -0.70
    sell
    -0.64
    iso
    -0.63
    flies
    -0.63
    borne
    -0.63
    headed
    -0.63
    pe
    -0.62
    cut
    -0.62
    POSITIVE LOGITS
    ivity
    0.85
    ucky
    0.82
     participation
    0.75
    SN
    0.73
     Participation
    0.72
     participate
    0.72
    ivities
    0.70
    lees
    0.68
     participates
    0.66
    ACTION
    0.65
    Activations Density 0.039%

    No Known Activations