© 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. 1751
    Prev
    Next
    INDEX
    Explanations

    mentions of sports drafts and selections

    oai_token-act-pair · gpt-3.5-turbo

    references 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 @ 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
    interrupted
    -0.80
     outage
    -0.80
    clips
    -0.77
     vibrations
    -0.77
     intermitt
    -0.74
    stood
    -0.74
     Siren
    -0.72
     interrupted
    -0.72
    ience
    -0.69
     coping
    -0.68
    POSITIVE LOGITS
     lottery
    1.17
    Draft
    1.11
     draft
    0.96
     Draft
    0.87
     waivers
    0.86
    Reward
    0.84
    Pick
    0.83
     Heisman
    0.79
    rafted
    0.78
     Rookie
    0.78
    Activations Density 0.280%

    No Known Activations