© 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. 11-RES-JB
    11. 2599
    Prev
    Next
    INDEX
    Explanations

    phrases related to involvement or participation in activities

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "engage" and its variations, indicating a focus on participation or involvement in various activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ahon
    -0.68
    ough
    -0.61
    dylib
    -0.60
    taker
    -0.59
     overrun
    -0.58
    say
    -0.57
    aring
    -0.57
    TI
    -0.55
    pler
    -0.54
    come
    -0.54
    POSITIVE LOGITS
    igate
    0.85
     with
    0.82
     in
    0.77
     actively
    0.76
    ments
    0.75
    forces
    0.70
    antically
    0.70
    iments
    0.69
     territ
    0.69
    ingly
    0.69
    Activations Density 0.048%

    No Known Activations