© 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. 11-RES-JB
    11. 16446
    Prev
    Next
    INDEX
    Explanations

    specific statistics related to sports performance

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to sports statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    taboola
    -0.62
     UNCLASSIFIED
    -0.62
    /(
    -0.61
    FORE
    -0.60
    catentry
    -0.60
    LAB
    -0.59
     param
    -0.59
    soType
    -0.58
     Creat
    -0.57
    uddin
    -0.57
    POSITIVE LOGITS
     57
    0.95
     52
    0.94
     39
    0.93
     59
    0.93
     46
    0.93
     376
    0.92
     54
    0.92
     44
    0.92
     82
    0.91
     61
    0.91
    Activations Density 0.061%

    No Known Activations