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

    Neuronpedia

    Jacobian LensNEW
    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. 8-RES-JB
    11. 1062
    Prev
    Next
    INDEX
    Explanations

    references to specific picks in sports drafts

    oai_token-act-pair · gpt-3.5-turbo

    terms related to draft picks in sports

    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
    -0.83
    cers
    -0.77
     tempor
    -0.75
    sth
    -0.75
    uras
    -0.74
     hem
    -0.71
    igi
    -0.69
     lapt
    -0.67
    sten
    -0.65
     ejac
    -0.64
    POSITIVE LOGITS
     picks
    0.88
     compens
    0.86
     lottery
    0.85
     (#
    0.84
     pick
    0.81
    士
    0.78
    Draft
    0.78
     cornerback
    0.77
     undrafted
    0.75
    ãģ®æ
    0.75
    Activations Density 0.047%

    No Known Activations