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. 6-RES-JB
    6. 9488
    Prev
    Next
    INDEX
    Explanations

    references related to sports events and locations

    oai_token-act-pair · gpt-3.5-turbo

    emotional responses related to mourning and loss in the context of sports or fandom

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    indal
    -0.72
     Bastard
    -0.67
    ADVERTISEMENT
    -0.66
     Wage
    -0.64
     Dek
    -0.63
     Substance
    -0.61
    âĻ¥
    -0.61
    phasis
    -0.59
    Footnote
    -0.58
     Ratings
    -0.58
    POSITIVE LOGITS
     photographed
    0.75
     photographs
    0.72
     gunmen
    0.70
     skyline
    0.70
    window
    0.68
    ideshow
    0.68
     makeshift
    0.65
     flashes
    0.65
     reacts
    0.65
     firefighters
    0.64
    Activations Density 0.111%

    No Known Activations