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. 9-RES-JB
    6. 4472
    Prev
    Next
    INDEX
    Explanations

    dates in the format "year.month."

    oai_token-act-pair · gpt-3.5-turbo

    references to news articles or reports

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Newsletter
    -0.99
    ··
    -0.92
    âϦ
    -0.85
    âĢ¢âĢ¢
    -0.84
    âĢ¢
    -0.78
     â̦
    -0.76
    â̦â̦
    -0.73
    advertisement
    -0.72
     âĨĴ
    -0.71
    halla
    -0.70
    POSITIVE LOGITS
     REUTERS
    1.07
    FILE
    0.96
     Reuters
    0.90
     OPEC
    0.73
    Sl
    0.72
     HSBC
    0.67
    ideshow
    0.67
    )=(
    0.66
     Tayyip
    0.66
     petrol
    0.64
    Activations Density 0.188%

    No Known Activations