© 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. 2650
    Prev
    Next
    INDEX
    Explanations

    the name "Nancy"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Nancy"

    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
    adr
    -0.87
    tered
    -0.75
    igated
    -0.71
    oning
    -0.71
    orescent
    -0.68
    orical
    -0.67
    points
    -0.67
    Spoiler
    -0.65
    upon
    -0.64
    EStreamFrame
    -0.64
    POSITIVE LOGITS
     Pelosi
    1.22
     Nancy
    0.97
     Drew
    0.86
     Grace
    0.80
     Reagan
    0.77
    theless
    0.74
     Loren
    0.73
    vier
    0.72
     Lan
    0.72
     Barbara
    0.70
    Activations Density 0.008%

    No Known Activations