© 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. 8-RES-JB
    11. 6821
    Prev
    Next
    INDEX
    Explanations

    sports-related words and statistics

    oai_token-act-pair · gpt-3.5-turbo

    statistical references related to sports performance

    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
    insula
    -0.78
    riad
    -0.74
    abus
    -0.73
    Enlarge
    -0.72
    argon
    -0.70
    mop
    -0.70
     Canaver
    -0.70
    Panel
    -0.67
    rag
    -0.66
    udeb
    -0.66
    POSITIVE LOGITS
     averaging
    1.28
     averaged
    1.28
     scoring
    1.22
     victories
    1.14
     scored
    1.12
     earned
    1.07
     earning
    1.06
     exce
    1.04
     racked
    1.03
     batted
    1.00
    Activations Density 0.459%

    No Known Activations