© 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. 0-RES-JB
    11. 5246
    Prev
    Next
    INDEX
    Explanations

    references to the University of Southern California (USC)

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the University of Southern California (USC)

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tofu
    -0.74
     Booster
    -0.73
     Architects
    -0.71
     Rahman
    -0.70
     Nanto
    -0.68
    RI
    -0.68
     ROB
    -0.66
     Towers
    -0.65
     inhibitor
    -0.65
    iHUD
    -0.65
    POSITIVE LOGITS
     USC
    1.92
    lust
    1.80
     lust
    1.40
    thirst
    1.06
    usp
    1.02
     Wick
    1.01
     Hud
    0.99
    ubb
    0.98
    usc
    0.95
    snap
    0.89
    Activations Density 0.047%

    No Known Activations