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

    Neuronpedia

    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. 22484
    Prev
    Next
    INDEX
    Explanations

    quantities related to sports plays, particularly those involving tackling

    oai_token-act-pair · gpt-3.5-turbo

    terms related to defensive statistics in 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
     taste
    -0.64
    una
    -0.63
     Zoro
    -0.63
    ren
    -0.62
    gor
    -0.62
    mod
    -0.62
    eren
    -0.60
     lie
    -0.59
     Noble
    -0.58
    NG
    -0.58
    POSITIVE LOGITS
     tackles
    3.83
     tackle
    1.51
     tackled
    1.44
     dives
    1.43
     sacks
    1.42
     interceptions
    1.40
     tackling
    1.39
    tackle
    1.35
     rebounds
    1.24
     catches
    1.21
    Activations Density 0.017%

    No Known Activations