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. 10-RES-JB
    6. 22811
    Prev
    Next
    INDEX
    Explanations

    statements made by spokespersons or officials in news articles

    oai_token-act-pair · gpt-3.5-turbo

    quotes from officials, particularly related to military and governmental statements

    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
    etsy
    -0.74
     Millennials
    -0.72
    ãĤ¦ãĤ¹
    -0.70
     chirop
    -0.70
     Founders
    -0.66
     Briggs
    -0.65
    Consider
    -0.64
     Invention
    -0.62
     Catalyst
    -0.62
     Proposition
    -0.62
    POSITIVE LOGITS
     Xin
    1.03
     AFP
    1.02
     Reuters
    0.98
     REUTERS
    0.90
     Arabic
    0.90
    zbollah
    0.89
     Sana
    0.86
    ansk
    0.86
     quoted
    0.85
     Kurdish
    0.85
    Activations Density 0.404%

    No Known Activations