© 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. 23900
    Prev
    Next
    INDEX
    Explanations

    specific mentions of draft picks in various sports leagues

    oai_token-act-pair · gpt-3.5-turbo

    information related to sports drafts and player selections

    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
     prosec
    -0.70
     horizont
    -0.69
     briefed
    -0.67
     lia
    -0.66
     staffed
    -0.65
     reminders
    -0.64
     prosecutions
    -0.63
    enance
    -0.62
     hosts
    -0.62
    zee
    -0.61
    POSITIVE LOGITS
    rafted
    0.94
    Draft
    0.90
    venth
    0.83
     seventh
    0.80
     sixth
    0.78
    HL
    0.77
    NFL
    0.76
     draft
    0.74
    lator
    0.73
     Supplemental
    0.73
    Activations Density 0.106%

    No Known Activations