Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 21226
    Prev
    Next
    INDEX
    Explanations

    terms related to statistics and performance in sports, specifically focusing on aspects related to scoring points

    oai_token-act-pair · gpt-3.5-turbo

    terms related to scoring in sports, particularly in basketball and football

    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
     NHS
    -0.71
     Governments
    -0.69
    XM
    -0.68
    schild
    -0.67
     Yen
    -0.66
    fam
    -0.65
     Xen
    -0.65
    CN
    -0.65
    cash
    -0.64
    çͰ
    -0.63
    POSITIVE LOGITS
     kicker
    1.01
     scorer
    0.92
     touchdown
    0.88
     offense
    0.85
     scoreboard
    0.82
     touchdowns
    0.79
     fullback
    0.78
     kickoff
    0.78
     shootout
    0.76
     finishes
    0.76
    Activations Density 0.149%

    No Known Activations