© 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. 10-RES-JB
    11. 12063
    Prev
    Next
    INDEX
    Explanations

    words related to sports and playing in sports games

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    leans
    -0.71
    imb
    -0.71
    gement
    -0.68
    venants
    -0.65
    ================================================================
    -0.65
    zanne
    -0.65
    ayers
    -0.64
    sav
    -0.64
    brow
    -0.63
    geries
    -0.63
    POSITIVE LOGITS
     alongside
    0.98
     colleg
    0.96
     fullback
    0.87
     against
    0.87
     basketball
    0.86
     football
    0.84
     professionally
    0.83
     shortstop
    0.82
     rugby
    0.81
     sparing
    0.81
    Activations Density 0.052%

    No Known Activations