© 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. 7571
    Prev
    Next
    INDEX
    Explanations

    keywords related to weight or body fat

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "fat" and its variations in various contexts

    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
    SPONSORED
    -0.86
     Ascend
    -0.68
    Sensor
    -0.68
     Mend
    -0.66
     Vaugh
    -0.65
     Emin
    -0.63
     Rowling
    -0.63
    ä
    -0.63
     Doct
    -0.62
    shire
    -0.61
    POSITIVE LOGITS
    igue
    1.40
    hered
    1.24
    ality
    1.10
    ty
    1.03
    ima
    1.00
    uous
    0.94
    Wallet
    0.91
    cats
    0.91
    wa
    0.90
    fing
    0.85
    Activations Density 0.038%

    No Known Activations