© 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. 12857
    Prev
    Next
    INDEX
    Explanations

    words related to the sport of water polo

    oai_token-act-pair · gpt-3.5-turbo

    references to political-related terms

    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
    SPONSORED
    -0.78
     Davis
    -0.74
    ensen
    -0.73
     Advent
    -0.73
     Cain
    -0.73
    ogle
    -0.71
     Hag
    -0.69
    Davis
    -0.68
    eat
    -0.68
     NAS
    -0.67
    POSITIVE LOGITS
     pol
    4.04
     Pol
    1.92
    pol
    1.83
     polish
    1.71
    Pol
    1.71
    POL
    1.49
     Polo
    1.47
     POL
    1.44
     polio
    1.16
     Polish
    0.97
    Activations Density 0.017%

    No Known Activations