© 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. 20825
    Prev
    Next
    INDEX
    Explanations

    the names of individuals associated with sports teams

    oai_token-act-pair · gpt-3.5-turbo

    parentheses and related structures in the text

    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
     following
    -0.70
     hitters
    -0.69
     consist
    -0.66
     normalized
    -0.66
     shaming
    -0.65
     demographic
    -0.65
     broadly
    -0.65
     ingredients
    -0.65
     overl
    -0.64
     circulating
    -0.63
    POSITIVE LOGITS
    USA
    1.04
    Atl
    1.04
    who
    0.98
    voc
    0.97
    University
    0.97
    Assistant
    0.97
    cox
    0.92
    Columb
    0.91
    Ph
    0.89
    lead
    0.89
    Activations Density 0.107%

    No Known Activations