Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 9800
    Prev
    Next
    INDEX
    Explanations

    sport strategies and positions

    oai_token-act-pair · gpt-3.5-turbo

    numerical information or statistics related to player performance

    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
     Thanksgiving
    -0.77
     Honolulu
    -0.76
    iatus
    -0.75
     Anchorage
    -0.75
     TMZ
    -0.75
     leukemia
    -0.75
     Amtrak
    -0.74
     Summit
    -0.73
     FDA
    -0.73
     Montana
    -0.73
    POSITIVE LOGITS
     midfield
    1.40
     centre
    1.18
     centrally
    1.17
     defences
    1.17
     strikers
    1.15
     midfielder
    1.13
     drib
    1.13
     possession
    1.12
    Liverpool
    1.12
     striker
    1.11
    Activations Density 0.286%

    No Known Activations