© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 13572
    Prev
    Next
    INDEX
    Explanations

    people or individuals mentioned in the text

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "who" followed by significant activation values, indicating a focus on people and their roles or actions within a context

    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
     Curious
    -0.85
    Researchers
    -0.74
    Artist
    -0.71
     decoding
    -0.69
     Pieces
    -0.67
     Mortal
    -0.67
     Weird
    -0.66
     Researchers
    -0.66
     Shutterstock
    -0.65
    Anonymous
    -0.65
    POSITIVE LOGITS
     campaigned
    1.71
     presided
    1.46
     oversaw
    1.34
     opposes
    1.28
     appoint
    1.27
     vowed
    1.27
     pledged
    1.21
     championed
    1.21
     vetoed
    1.20
     vows
    1.18
    Activations Density 0.311%

    No Known Activations