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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 4124
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific person with the name "Usk" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    the name "Tusk" mentioned in various contexts

    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
     addresses
    -0.66
     routers
    -0.63
     disclaimer
    -0.63
     trans
    -0.63
     mustard
    -0.62
     Queens
    -0.62
     evangel
    -0.61
     receivers
    -0.61
     controllers
    -0.61
     forwarding
    -0.60
    POSITIVE LOGITS
    usk
    4.83
    usc
    1.36
    usky
    1.32
    us
    1.09
    uders
    1.04
    ÄŁ
    1.03
    arak
    1.03
    ussen
    1.02
     Dusk
    1.00
    uden
    0.99
    Activations Density 0.026%

    No Known Activations