© 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. 7-RES-JB
    11. 6418
    Prev
    Next
    INDEX
    Explanations

    mentions of football (soccer) matches

    oai_token-act-pair · gpt-3.5-turbo

    references to sports teams and matchups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tymology
    -0.73
     lawy
    -0.72
     memos
    -0.71
    minist
    -0.71
     journals
    -0.68
     niche
    -0.68
     document
    -0.65
     shorthand
    -0.65
    pmwiki
    -0.63
     lifespan
    -0.63
    POSITIVE LOGITS
     rivals
    0.81
    matched
    0.80
     rival
    0.71
    ubi
    0.68
     Titans
    0.68
    adr
    0.67
     opponents
    0.67
     Rams
    0.67
     foe
    0.66
    htar
    0.66
    Activations Density 0.249%

    No Known Activations