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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 8082
    Prev
    Next
    INDEX
    Explanations

    details related to sports statistics and player performance

    oai_token-act-pair · gpt-3.5-turbo

    specific dates, times, and events related to sports and politics

    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
    .:
    -0.97
    .):
    -0.95
    .).
    -0.95
    .?
    -0.86
    .*
    -0.86
    *:
    -0.83
    .ãĢį
    -0.81
    .�
    -0.81
    .</
    -0.78
     ðŁĻĤ
    -0.77
    POSITIVE LOGITS
     owing
    0.80
     following
    0.79
     amid
    0.78
     after
    0.76
     but
    0.76
     prompting
    0.73
     thanks
    0.67
     due
    0.67
     fearing
    0.66
    due
    0.65
    Activations Density 0.944%

    No Known Activations