© 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. 16610
    Prev
    Next
    INDEX
    Explanations

    phrases related to the construction or design of objects

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating functionality or purpose

    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
     Perspective
    -0.70
    started
    -0.68
    berries
    -0.65
    owners
    -0.64
     goodbye
    -0.62
     Investments
    -0.59
     Owners
    -0.59
     founded
    -0.57
     Property
    -0.57
    opened
    -0.57
    POSITIVE LOGITS
     withstand
    1.56
     accommodate
    1.35
     resemble
    1.28
     maximize
    1.18
     cope
    1.18
     handle
    1.13
     coincide
    1.09
     mimic
    1.09
     simulate
    1.08
     emulate
    1.08
    Activations Density 0.159%

    No Known Activations