© 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. 24178
    Prev
    Next
    INDEX
    Explanations

    specific names, especially "Liz."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Liz."

    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
    asar
    -0.69
    Ħ¢
    -0.69
     Archdemon
    -0.66
     restraining
    -0.66
     eve
    -0.64
    quartered
    -0.63
     night
    -0.63
     day
    -0.63
    ¥ŀ
    -0.63
    mble
    -0.62
    POSITIVE LOGITS
     Liz
    0.98
    iverpool
    0.85
    otte
    0.77
     Lemon
    0.75
    Lenin
    0.75
    MJ
    0.74
    wei
    0.73
     Cheney
    0.73
    enegger
    0.72
    ibly
    0.72
    Activations Density 0.021%

    No Known Activations