© 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. 16677
    Prev
    Next
    INDEX
    Explanations

    keywords related to political and international affairs

    oai_token-act-pair · gpt-3.5-turbo

    topics related to governmental and regulatory issues

    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
    !".
    -0.60
    asters
    -0.57
     frag
    -0.55
    %.
    -0.55
     ILCS
    -0.54
    $.
    -0.54
    ITNESS
    -0.54
     "+
    -0.54
     Gadget
    -0.54
    "!
    -0.52
    POSITIVE LOGITS
     coincides
    1.24
     coincided
    1.23
     hinges
    1.23
     stems
    1.13
     stemmed
    1.07
     underscores
    1.06
     owes
    1.04
     involves
    1.02
     culminated
    0.99
     rests
    0.99
    Activations Density 0.319%

    No Known Activations