© 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. 4-RES-JB
    11. 10919
    Prev
    Next
    INDEX
    Explanations

    phrases related to the name "Crosby."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific individuals, particularly athletes, in the text

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

    No Comments

    Negative Logits
    ican
    -0.69
    edIn
    -0.69
    arat
    -0.69
    wered
    -0.69
    entity
    -0.67
    IELD
    -0.66
     acquisition
    -0.65
     Renaissance
    -0.63
    ively
    -0.61
    FN
    -0.61
    POSITIVE LOGITS
    stal
    1.00
     Crosby
    0.94
    kefeller
    0.74
    stown
    0.74
    nr
    0.73
     Vaugh
    0.71
    pter
    0.70
    rier
    0.70
    rome
    0.69
    milo
    0.68
    Activations Density 0.029%

    No Known Activations