© 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. 2-RES-JB
    11. 1414
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Elizabeth"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name Elizabeth

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ursed
    -0.83
    unal
    -0.80
    ebin
    -0.79
    awaru
    -0.76
    ãĥ£
    -0.76
    acca
    -0.75
    shapeshifter
    -0.73
    yright
    -0.71
    alien
    -0.69
    ²¾
    -0.68
    POSITIVE LOGITS
     Elizabeth
    1.07
     Warren
    1.02
     Howell
    0.98
     Holmes
    0.88
     Taylor
    0.85
     Williams
    0.83
     Dodd
    0.82
    Elizabeth
    0.81
     Tud
    0.81
     Liu
    0.80
    Activations Density 0.006%

    No Known Activations