© 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. 9-RES-JB
    11. 18494
    Prev
    Next
    INDEX
    Explanations

    words related to different types of events or occasions, particularly involving food, entertainment, and employment

    oai_token-act-pair · gpt-3.5-turbo

    references to social events and gatherings, particularly barbecues and awards

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Americ
    -0.61
    atars
    -0.57
    ropolitan
    -0.55
    fram
    -0.54
    TextColor
    -0.54
    abul
    -0.53
    ãĤª
    -0.53
     Zup
    -0.52
    escription
    -0.52
    aughtered
    -0.51
    POSITIVE LOGITS
     anyways
    0.66
     anyway
    0.66
     itself
    0.65
     alone
    0.63
     standpoint
    0.63
     moniker
    0.62
     induction
    0.61
     debacle
    0.60
     stems
    0.60
     because
    0.60
    Activations Density 0.621%

    No Known Activations