© 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. 9-RES-JB
    11. 2322
    Prev
    Next
    INDEX
    Explanations

    phrases related to construction and design

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating purpose or design in construction

    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
    calling
    -0.77
     Perspective
    -0.75
     Thoughts
    -0.67
    thinking
    -0.65
    comments
    -0.65
    broken
    -0.64
     Words
    -0.63
     Conversation
    -0.63
    started
    -0.62
    spection
    -0.61
    POSITIVE LOGITS
     withstand
    1.68
     accommodate
    1.56
     maximize
    1.39
     resemble
    1.28
     satisfy
    1.28
     cope
    1.24
     minimize
    1.22
     optimize
    1.21
     facilitate
    1.20
     operate
    1.19
    Activations Density 0.178%

    No Known Activations