© 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. 1-RES-JB
    11. 16331
    Prev
    Next
    INDEX
    Explanations

    words related to winning or achieving success

    oai_token-act-pair · gpt-3.5-turbo

    references to a prestigious sports title or championship

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    glers
    -0.77
    draw
    -0.75
    geist
    -0.72
     Twain
    -0.72
     Neighbor
    -0.71
    ARB
    -0.71
     MacArthur
    -0.71
     Reporter
    -0.70
     Sue
    -0.70
    CV
    -0.70
    POSITIVE LOGITS
     prem
    1.37
    iership
    1.18
     oun
    0.96
     comr
    0.95
    antle
    0.94
     gobl
    0.93
    merce
    0.92
    wcs
    0.92
     mosqu
    0.91
     unden
    0.89
    Activations Density 0.007%

    No Known Activations