© 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. 7-RES-JB
    11. 13495
    Prev
    Next
    INDEX
    Explanations

    topics related to sports and entertainment

    oai_token-act-pair · gpt-3.5-turbo

    connections between different forms of entertainment and cultural expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ledged
    -0.87
    ptoms
    -0.70
    usted
    -0.69
    placed
    -0.68
    ername
    -0.67
    uler
    -0.66
     rede
    -0.65
     Majority
    -0.64
     superiors
    -0.63
     Pelosi
    -0.62
    POSITIVE LOGITS
     entertainment
    1.01
    Music
    0.91
     cinema
    0.88
     Classics
    0.88
    music
    0.87
     movies
    0.87
     genres
    0.87
     SPORTS
    0.85
     opera
    0.84
     music
    0.84
    Activations Density 0.356%

    No Known Activations