© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 2858
    Prev
    Next
    INDEX
    Explanations

    phrases related to sports statistics, such as specific player actions and achievements

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate a measurement or statistical context 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
    pora
    -0.89
    quartered
    -0.81
    helle
    -0.77
     Cosponsors
    -0.72
    toc
    -0.66
    microsoft
    -0.66
    anwhile
    -0.66
    tsy
    -0.65
    itaire
    -0.63
     coerc
    -0.61
    POSITIVE LOGITS
     preseason
    1.00
     Champions
    0.93
     coaching
    0.91
     playoff
    0.88
     postseason
    0.87
    juries
    0.85
     Rookie
    0.81
     sorts
    0.78
     offseason
    0.78
     scrimmage
    0.77
    Activations Density 0.244%

    No Known Activations