© 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. 0-RES-JB
    11. 473
    Prev
    Next
    INDEX
    Explanations

    references to the name "Clinton"

    oai_token-act-pair · gpt-3.5-turbo

    the name "Clinton"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     crew
    -0.76
     curse
    -0.66
     fet
    -0.65
     load
    -0.64
     relief
    -0.63
     Tier
    -0.63
     istg
    -0.62
     AU
    -0.62
     AA
    -0.62
     wise
    -0.62
    POSITIVE LOGITS
    inton
    4.70
    INTON
    1.74
    inson
    1.39
    INGTON
    1.17
    eston
    1.14
    ington
    1.08
    enton
    1.02
    clinton
    1.01
    entin
    0.97
    ixon
    0.97
    Activations Density 0.013%

    No Known Activations