© 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 EvalsExportsinterp-engineNEWAPI 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. 24353
    Prev
    Next
    INDEX
    Explanations

    statistical performance metrics in sports

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating leadership or dominance in statistics

    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
    entric
    -0.73
    _____
    -0.70
     mart
    -0.65
     licences
    -0.62
     vic
    -0.60
     breeze
    -0.60
    yah
    -0.59
    shi
    -0.58
     RELE
    -0.58
    mit
    -0.57
    POSITIVE LOGITS
     scorer
    0.97
     rusher
    0.82
    hunt
    0.77
    combe
    0.75
    ranked
    0.69
    bare
    0.67
    interstitial
    0.67
    cedes
    0.65
     ranks
    0.64
    pick
    0.64
    Activations Density 0.044%

    No Known Activations