© 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 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. 16704
    Prev
    Next
    INDEX
    Explanations

    references to sports events and teams

    oai_token-act-pair · gpt-3.5-turbo

    sentences with numerical values or references to scores

    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
     barr
    -0.91
     cens
    -0.85
     censored
    -0.83
     foc
    -0.83
     migrant
    -0.83
     mystic
    -0.82
     stigmat
    -0.81
     enqu
    -0.80
     commissions
    -0.80
     polic
    -0.79
    POSITIVE LOGITS
    Coach
    1.79
    Players
    1.67
    ESPN
    1.65
    Article
    1.62
    Thumbnail
    1.62
    NFL
    1.53
    Detroit
    1.53
    MORE
    1.52
    Fans
    1.52
    Playing
    1.49
    Activations Density 0.197%

    No Known Activations