© 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. 10-RES-JB
    11. 3186
    Prev
    Next
    INDEX
    Explanations

    mentions of people dressing up in various costumes or attire

    oai_token-act-pair · gpt-3.5-turbo

    references to dressing up or costumes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SHIP
    -0.85
    venants
    -0.69
    vd
    -0.67
    Focus
    -0.66
    stem
    -0.65
    sth
    -0.65
    nir
    -0.65
     FTA
    -0.64
    esi
    -0.64
    nesota
    -0.63
    POSITIVE LOGITS
     gown
    1.03
     rehearsal
    1.02
     attire
    0.92
     rehears
    0.92
     robes
    0.91
     uniforms
    0.88
     shirts
    0.84
     costumes
    0.84
     worn
    0.84
     dresses
    0.82
    Activations Density 0.045%

    No Known Activations