© 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. 8-RES-JB
    11. 22385
    Prev
    Next
    INDEX
    Explanations

    words related to the performance or form of a player in a sports season

    oai_token-act-pair · gpt-3.5-turbo

    references to reliability and performance 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 @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ®
    -0.76
    aucus
    -0.75
    orah
    -0.67
     Locations
    -0.67
     Pledge
    -0.65
     âĨij
    -0.65
     Nath
    -0.63
     Hundreds
    -0.62
     Lawyers
    -0.61
    Cath
    -0.61
    POSITIVE LOGITS
     athlet
    1.16
     offensively
    1.16
     rookie
    1.12
     teammates
    1.11
     teammate
    1.09
     Rookie
    1.08
     athleticism
    1.06
     linem
    1.01
     defensively
    0.99
     positional
    0.99
    Activations Density 0.875%

    No Known Activations