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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 10-RES-JB
    6. 8820
    Prev
    Next
    INDEX
    Explanations

    phrases related to sports news and insights, particularly from specific sports reporting sources

    oai_token-act-pair · gpt-3.5-turbo

    mentions of NFL insiders or reports related to sports news

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vt
    -0.90
    chin
    -0.84
    netflix
    -0.80
    wikipedia
    -0.73
     Gutenberg
    -0.72
    mits
    -0.68
     UNESCO
    -0.67
     Canaveral
    -0.66
     Turing
    -0.66
    esson
    -0.65
    POSITIVE LOGITS
     FANTASY
    1.06
     Insider
    1.03
    Sports
    1.02
     Sports
    1.00
     scouting
    0.99
     Rookie
    0.93
     scouts
    0.91
     Composite
    0.91
    Football
    0.91
     preseason
    0.91
    Activations Density 0.122%

    No Known Activations