© 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. 6-RES-JB
    11. 11915
    Prev
    Next
    INDEX
    Explanations

    references to clothing items, specifically focusing on long-sleeved shirts

    oai_token-act-pair · gpt-3.5-turbo

    the presence of the term "lee" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Seym
    -0.82
    onut
    -0.76
    rices
    -0.75
    achu
    -0.75
    urated
    -0.71
    folios
    -0.70
    romeda
    -0.70
    ificial
    -0.70
    rait
    -0.69
    ifact
    -0.68
    POSITIVE LOGITS
    pless
    1.09
    ce
    1.00
    ves
    0.95
    vec
    0.92
    lee
    0.91
    gha
    0.90
    ved
    0.87
    vel
    0.87
    scill
    0.77
    urring
    0.74
    Activations Density 0.046%

    No Known Activations