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

    Neuronpedia

    Jacobian LensNEW
    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. 9-RES-JB
    11. 18381
    Prev
    Next
    INDEX
    Explanations

    mentions of specific game numbers in a sports context

    oai_token-act-pair · gpt-3.5-turbo

    references to specific games or matches in a sports context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    amina
    -0.66
    tap
    -0.66
    ometers
    -0.65
    aying
    -0.64
    robe
    -0.63
    itud
    -0.63
    company
    -0.63
    license
    -0.62
    ordinate
    -0.62
    atan
    -0.60
    POSITIVE LOGITS
     onwards
    0.97
     onward
    0.90
    âĢ²
    0.71
     finale
    0.70
     Prol
    0.68
     Recap
    0.66
     Madness
    0.66
     Redux
    0.65
    ITIES
    0.65
     Finals
    0.65
    Activations Density 0.078%

    No Known Activations