© 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. 8-RES-JB
    11. 3161
    Prev
    Next
    INDEX
    Explanations

    references to individuals named Antonio

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Antonio"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lasses
    -1.01
    igation
    -0.80
    cipled
    -0.76
    eled
    -0.75
    recy
    -0.73
    glers
    -0.69
    etooth
    -0.69
    nda
    -0.68
    aration
    -0.67
    drop
    -0.67
    POSITIVE LOGITS
     Spurs
    0.88
     ç¥ŀ
    0.73
    quit
    0.71
    omy
    0.70
     XIII
    0.70
    illo
    0.69
     Hort
    0.68
     Scorp
    0.68
    oise
    0.68
     Antonio
    0.68
    Activations Density 0.037%

    No Known Activations