© 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. 10-RES-JB
    11. 12818
    Prev
    Next
    INDEX
    Explanations

    the word "football" and related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to football as a sport

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    EStream
    -0.67
     Ples
    -0.65
    aft
    -0.64
    windows
    -0.63
    tle
    -0.63
    cius
    -0.63
     Norn
    -0.61
    oldemort
    -0.59
     Abrams
    -0.59
     Nas
    -0.58
    POSITIVE LOGITS
     stadiums
    1.03
    ing
    1.02
    ers
    0.94
    club
    0.86
     clubs
    0.84
     stadium
    0.82
    sch
    0.80
     club
    0.79
    sburg
    0.79
    players
    0.78
    Activations Density 0.029%

    No Known Activations