© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 822
    Prev
    Next
    INDEX
    Explanations

    words related to committing an action or making a commitment

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "commit" associated with various actions or behaviors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uyomi
    -0.71
     Ain
    -0.70
     Takeru
    -0.69
    ****************
    -0.66
    dayName
    -0.66
     Plat
    -0.66
     Cheong
    -0.65
     Ames
    -0.64
    spr
    -0.63
    adish
    -0.60
    POSITIVE LOGITS
     commit
    1.01
    commit
    0.97
     commits
    0.94
     committed
    0.88
     committing
    0.83
    utions
    0.78
    lesh
    0.77
    yards
    0.76
     Commit
    0.72
    erences
    0.71
    Activations Density 0.008%

    No Known Activations