© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 1903
    Prev
    Next
    INDEX
    Explanations

    sports-related content, focusing on football in particular

    oai_token-act-pair · gpt-3.5-turbo

    references to players' performance and potential in sports contexts

    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
     apologised
    -0.86
     apologise
    -0.83
    yrics
    -0.79
     humour
    -0.73
     organisers
    -0.71
     metre
    -0.71
     backstage
    -0.70
     lyrics
    -0.70
     commem
    -0.70
     quotations
    -0.70
    POSITIVE LOGITS
     matchup
    0.99
    Draft
    0.98
    Pred
    0.95
    nesota
    0.95
     rookie
    0.94
     sleeper
    0.93
     Prediction
    0.92
     Rookie
    0.91
    omever
    0.90
     prospects
    0.89
    Activations Density 0.726%

    No Known Activations