© 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. 7237
    Prev
    Next
    INDEX
    Explanations

    phrases related to observations or facts, often using words like "is" and "that."

    oai_token-act-pair · gpt-3.5-turbo

    discussions centered around challenges and criticisms in sports and startups

    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
     Pwr
    -0.77
    Gov
    -0.77
    Judge
    -0.76
    flag
    -0.76
    Attorney
    -0.76
    Senator
    -0.75
    realDonaldTrump
    -0.75
    ificantly
    -0.75
     Corker
    -0.72
    TRUMP
    -0.71
    POSITIVE LOGITS
     everything
    1.13
     creativity
    1.11
     everyone
    1.04
     beginners
    1.03
     most
    0.97
     gadgets
    0.97
     audiences
    0.97
     they
    0.96
     simplicity
    0.95
     there
    0.94
    Activations Density 0.448%

    No Known Activations