© 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. 3-RES-JB
    11. 10645
    Prev
    Next
    INDEX
    Explanations

    phrases related to sports events, specifically halftime and timeouts

    oai_token-act-pair · gpt-3.5-turbo

    references to halftime events and associated activities in a sports context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    doms
    -0.81
    ogy
    -0.76
    ocus
    -0.72
    urat
    -0.72
    uron
    -0.69
    hood
    -0.66
    ozy
    -0.65
    remlin
    -0.65
    olog
    -0.65
    istan
    -0.64
    POSITIVE LOGITS
     halftime
    1.16
    ftime
    0.90
     kickoff
    0.75
    iday
    0.71
    brance
    0.67
    steen
    0.67
    nesday
    0.66
    hews
    0.66
    pter
    0.65
     Fridays
    0.63
    Activations Density 0.008%

    No Known Activations