© 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. 3230
    Prev
    Next
    INDEX
    Explanations

    proper nouns and specific terms within text

    oai_token-act-pair · gpt-3.5-turbo

    end-of-document markers or signals indicating the conclusion of a text

    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
     somehow
    -0.63
    ledge
    -0.63
     apart
    -0.61
    fulness
    -0.60
    ality
    -0.58
     alongside
    -0.58
    oyer
    -0.58
    *.
    -0.58
    /"
    -0.56
    aday
    -0.56
    POSITIVE LOGITS
     Month
    1.06
     foregoing
    0.93
     Americas
    0.87
     utmost
    0.86
     Ancients
    0.86
     Year
    0.81
     Week
    0.80
     Confederacy
    0.73
     sexes
    0.72
     millennium
    0.72
    Activations Density 0.057%

    No Known Activations