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

    Neuronpedia

    Jacobian LensNEW
    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. 13579
    Prev
    Next
    INDEX
    Explanations

    articles of clothing

    oai_token-act-pair · gpt-3.5-turbo

    clothing and apparel-related terms

    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
     behavi
    -0.68
    íķ
    -0.68
     disinformation
    -0.68
     pandemonium
    -0.67
     misinformation
    -0.66
     insanity
    -0.66
     Depend
    -0.65
    SPONSORED
    -0.64
    terday
    -0.63
    utenberg
    -0.63
    POSITIVE LOGITS
    outer
    1.02
    anium
    1.01
    aft
    1.00
    ippers
    1.00
    pron
    0.97
    lasses
    0.94
    ilt
    0.92
     sleeves
    0.92
     sleeve
    0.90
    oves
    0.90
    Activations Density 0.210%

    No Known Activations