© 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. 3-RES-JB
    11. 12041
    Prev
    Next
    INDEX
    Explanations

    mentions of specific individuals or places named "Booth"

    oai_token-act-pair · gpt-3.5-turbo

    references to a character named Booth

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    irements
    -0.86
    ARY
    -0.74
    ccording
    -0.72
    encers
    -0.71
    tymology
    -0.71
    HER
    -0.70
    Ec
    -0.68
    ATHER
    -0.68
    atives
    -0.68
    NING
    -0.67
    POSITIVE LOGITS
     Booth
    1.15
    otle
    0.77
    bugs
    0.77
     booth
    0.73
    bug
    0.72
     Racer
    0.70
     Wilde
    0.70
     Bunny
    0.70
    ureau
    0.70
    la
    0.69
    Activations Density 0.005%

    No Known Activations