© 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. 1-RES-JB
    11. 2803
    Prev
    Next
    INDEX
    Explanations

    mentions of the actor David Schwimmer

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific individuals and companies, particularly in the context of industry-related discussions

    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
    ysis
    -0.79
    hran
    -0.79
     ingred
    -0.74
    ¯¯¯¯
    -0.73
    20439
    -0.70
    ————————————————
    -0.70
    ynthesis
    -0.70
     suspic
    -0.69
    oshop
    -0.67
    etics
    -0.67
    POSITIVE LOGITS
     Schw
    0.97
    abee
    0.82
     Kuh
    0.80
    ument
    0.78
     Omaha
    0.75
     buck
    0.69
     hump
    0.68
    arrison
    0.68
     Canal
    0.66
    ceed
    0.66
    Activations Density 0.023%

    No Known Activations