© 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. 0-RES-JB
    11. 13320
    Prev
    Next
    INDEX
    Explanations

    specific terms related to a particular event or situation, such as "Sideline Football."

    oai_token-act-pair · gpt-3.5-turbo

    references to sports, specifically football

    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
    addin
    -0.81
    osta
    -0.67
    reditary
    -0.65
    ahs
    -0.64
     Learns
    -0.64
     Miliband
    -0.63
    avid
    -0.63
    rollers
    -0.63
    enson
    -0.62
     gasp
    -0.61
    POSITIVE LOGITS
    cale
    0.75
    antha
    0.73
    ãĤ©
    0.71
     Till
    0.70
    fen
    0.69
     [&
    0.68
    MB
    0.68
    Track
    0.67
    éŃĶ
    0.64
     landfall
    0.64
    Activations Density 0.000%

    No Known Activations