© 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. 10-RES-JB
    11. 18861
    Prev
    Next
    INDEX
    Explanations

    NFL-related statistics and rankings

    oai_token-act-pair · gpt-3.5-turbo

    references to sports leagues and rankings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    ban
    -0.68
    È
    -0.64
    bek
    -0.63
     Banner
    -0.62
    ollah
    -0.60
    =#
    -0.59
    embed
    -0.59
    changes
    -0.58
    uay
    -0.56
     Fukushima
    -0.56
    POSITIVE LOGITS
     standings
    1.34
     rankings
    1.17
     scoring
    1.01
     Rankings
    0.89
    behind
    0.88
     ranking
    0.83
     classification
    0.82
     charts
    0.81
     behind
    0.81
     hierarchy
    0.81
    Activations Density 0.174%

    No Known Activations