© 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
    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. 2697
    Prev
    Next
    INDEX
    Explanations

    terms related to sports scores, player drafts, and team grades

    oai_token-act-pair · gpt-3.5-turbo

    elements related to sports and team performance metrics

    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
    hex
    -0.74
     cant
    -0.66
     fluoride
    -0.65
     lawfully
    -0.64
     Etsy
    -0.64
    mobi
    -0.63
     ecological
    -0.62
     Canaver
    -0.62
     infinity
    -0.61
    realDonaldTrump
    -0.61
    POSITIVE LOGITS
     STATS
    1.42
     Prediction
    1.21
     Rankings
    1.18
     Picks
    1.18
     Playoffs
    1.14
     Rookie
    1.14
     Stats
    1.13
     Playoff
    1.13
     Ranking
    1.12
     Injury
    1.12
    Activations Density 0.251%

    No Known Activations