© 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. 10-RES-JB
    11. 24563
    Prev
    Next
    INDEX
    Explanations

    names of people in news articles

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals or entities associated with a significant incident or situation

    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
     rooting
    -0.78
     conflicts
    -0.73
     FIGHT
    -0.73
     conflict
    -0.73
     elim
    -0.73
     NEXT
    -0.73
     sustaining
    -0.72
     progress
    -0.70
     defin
    -0.70
     respect
    -0.69
    POSITIVE LOGITS
    Jones
    1.43
    Williams
    1.31
    Smith
    1.29
    Harris
    1.27
    Clark
    1.27
    Brown
    1.27
    Adams
    1.26
    Thompson
    1.24
    Hug
    1.24
    vous
    1.23
    Activations Density 0.029%

    No Known Activations