© 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. 19682
    Prev
    Next
    INDEX
    Explanations

    Italian names, specifically "Giuseppe"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of people, particularly in relation to names and professional titles

    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
    pin
    -0.83
    ayne
    -0.79
    akes
    -0.79
    uras
    -0.78
    reys
    -0.78
    phas
    -0.78
    der
    -0.77
    lap
    -0.77
    win
    -0.76
    rors
    -0.75
    POSITIVE LOGITS
    ppe
    0.87
    ppo
    0.82
     Carlo
    0.72
     Fo
    0.72
    oples
    0.70
     Caf
    0.69
     bushes
    0.67
     Purg
    0.66
    etter
    0.66
     Berger
    0.64
    Activations Density 0.016%

    No Known Activations