© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 11-RES-JB
    11. 22322
    Prev
    Next
    INDEX
    Explanations

    names of famous individuals or characters

    oai_token-act-pair · gpt-3.5-turbo

    names of notable individuals associated with film and television

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ighed
    -0.73
    unicip
    -0.69
    itionally
    -0.68
     unanimous
    -0.67
    cill
    -0.64
    erver
    -0.63
     moderation
    -0.63
    ollah
    -0.62
     preventive
    -0.62
    ĪĴ
    -0.61
    POSITIVE LOGITS
     Goes
    0.94
     Dracula
    0.91
     Pilgrim
    0.83
     Mysteries
    0.82
     Kubrick
    0.82
     Says
    0.81
     Frankenstein
    0.81
     Bones
    0.79
     Cage
    0.79
     Trilogy
    0.79
    Activations Density 0.236%

    No Known Activations