© 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. 13587
    Prev
    Next
    INDEX
    Explanations

    high-profile political figures

    oai_token-act-pair · gpt-3.5-turbo

    mentions of prominent political figures, particularly François Hollande

    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
     Addiction
    -0.77
    Ö¼
    -0.73
     Flavoring
    -0.71
    ãĤ£
    -0.69
     Akron
    -0.69
     Polaris
    -0.68
     Parenthood
    -0.65
    izations
    -0.65
     PAX
    -0.64
    iosyncr
    -0.64
    POSITIVE LOGITS
    enei
    1.11
     Hollande
    1.10
     Jinping
    1.06
    achev
    0.77
    ascus
    0.73
    llor
    0.72
    etta
    0.72
    oÄŁ
    0.71
    enstein
    0.71
    ande
    0.71
    Activations Density 0.013%

    No Known Activations