© 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. 11-RES-JB
    11. 14513
    Prev
    Next
    INDEX
    Explanations

    numeric values and statistical measurements related to sports and achievements

    oai_token-act-pair · gpt-3.5-turbo

    metrics that evaluate player performance in sports

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    atom
    -0.79
    auga
    -0.77
    enegger
    -0.73
    icro
    -0.72
    abel
    -0.70
    bara
    -0.70
    idon
    -0.68
    iane
    -0.67
     Hirosh
    -0.67
     sandy
    -0.66
    POSITIVE LOGITS
     Adjusted
    1.27
     percentage
    1.18
     +/-
    1.15
     percentile
    1.15
     efficiency
    1.14
     OPS
    1.14
     DV
    1.13
     Cors
    1.10
     scoring
    1.10
     Efficiency
    1.10
    Activations Density 0.206%

    No Known Activations