© 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. 3-RES-JB
    11. 14724
    Prev
    Next
    INDEX
    Explanations

    references to a sports team named "Spurs"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the San Antonio Spurs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    judicial
    -0.91
    ebin
    -0.66
    anced
    -0.66
     Turing
    -0.65
    ships
    -0.64
    obbies
    -0.64
    brance
    -0.63
    ownt
    -0.63
    oney
    -0.62
    llor
    -0.62
    POSITIVE LOGITS
     Hots
    1.25
     Spurs
    0.86
     Sauce
    0.83
    API
    0.79
     Bros
    0.75
    rament
    0.75
    heet
    0.74
    layer
    0.73
    caps
    0.71
    Fit
    0.71
    Activations Density 0.007%

    No Known Activations