© 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. 11-RES-JB
    11. 7798
    Prev
    Next
    INDEX
    Explanations

    terminology related to doping scandals in sports

    oai_token-act-pair · gpt-3.5-turbo

    references to official reports or findings related to doping cases

    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
    Ń·
    -0.86
    marg
    -0.77
    éĹ
    -0.77
    ĺħ
    -0.74
     Pixar
    -0.74
    aez
    -0.73
     siege
    -0.73
    rir
    -0.72
     crow
    -0.72
    oho
    -0.72
    POSITIVE LOGITS
     doping
    2.07
     steroid
    1.47
     Athlet
    1.45
     athletes
    1.42
     athlete
    1.38
    ADA
    1.32
     urine
    1.32
     athletics
    1.31
     suspensions
    1.29
     steroids
    1.28
    Activations Density 0.182%

    No Known Activations