© 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. 0-RES-JB
    11. 22194
    Prev
    Next
    INDEX
    Explanations

    phrases related to commencement or initiation

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "kicks off."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oric
    -0.67
    orne
    -0.65
     privately
    -0.63
    tile
    -0.63
    RN
    -0.61
    CI
    -0.61
    ond
    -0.60
     Intelligence
    -0.60
    vor
    -0.60
     Orn
    -0.59
    POSITIVE LOGITS
     kicks
    3.82
     kick
    2.17
     kicked
    1.94
     kicking
    1.93
    Kick
    1.54
    kick
    1.48
     punches
    1.43
     Kick
    1.37
     blows
    1.34
     kickoff
    1.34
    Activations Density 0.008%

    No Known Activations