© 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 EvalsExportsinterp-engineNEWAPI 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. 18967
    Prev
    Next
    INDEX
    Explanations

    proper names or entities, particularly when accompanied by a possessive apostrophe 's

    oai_token-act-pair · gpt-3.5-turbo

    certain characters or symbols used in the 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
     democracy
    -0.67
     ``
    -0.62
     Mobil
    -0.60
     dignity
    -0.58
     division
    -0.58
     uranium
    -0.57
     Democracy
    -0.57
     neut
    -0.56
     chart
    -0.56
     ................
    -0.55
    POSITIVE LOGITS
    s
    1.48
    t
    1.06
    sn
    1.01
    dq
    1.01
    shall
    0.99
    sat
    0.97
    d
    0.97
    sed
    0.96
    should
    0.95
    Pg
    0.95
    Activations Density 0.302%

    No Known Activations