© 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. 4-RES-JB
    11. 393
    Prev
    Next
    INDEX
    Explanations

    words related to time segments during sports events

    oai_token-act-pair · gpt-3.5-turbo

    references to halftime events and related activities in sports

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

    No Comments

    Negative Logits
    kson
    -0.74
    urat
    -0.71
    ogy
    -0.69
    uron
    -0.69
    doms
    -0.69
    kef
    -0.68
    ourke
    -0.67
    venants
    -0.67
    20439
    -0.67
    ================================================================
    -0.66
    POSITIVE LOGITS
     halftime
    1.12
    ftime
    0.94
     kickoff
    0.75
    iday
    0.74
    aneous
    0.71
    trop
    0.69
     Fridays
    0.69
    finals
    0.67
     quarters
    0.67
    noon
    0.65
    Activations Density 0.008%

    No Known Activations