© 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. 21678
    Prev
    Next
    INDEX
    Explanations

    information related to sports events and matches

    oai_token-act-pair · gpt-3.5-turbo

    boxing match details and outcomes

    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
    Newsletter
    -0.80
    ulhu
    -0.76
    PsyNetMessage
    -0.69
    relation
    -0.69
    dfx
    -0.69
    tracks
    -0.68
    aceae
    -0.67
    quist
    -0.65
     Cosponsors
    -0.65
    NPR
    -0.65
    POSITIVE LOGITS
     MMA
    1.16
     rematch
    1.07
     bout
    1.06
    weight
    1.01
     bouts
    1.00
    UFC
    0.99
     UFC
    0.96
    weights
    0.93
     boxing
    0.89
     Rouse
    0.88
    Activations Density 0.123%

    No Known Activations