© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 11641
    Prev
    Next
    INDEX
    Explanations

    sections of computer code

    oai_token-act-pair · gpt-3.5-turbo

    programming-related elements and structures, particularly those associated with databases and error handling

    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
     ancest
    -0.81
     paran
    -0.72
     plag
    -0.66
     acron
    -0.63
     privile
    -0.62
     AMA
    -0.61
    /)
    -0.60
     masculinity
    -0.60
    comings
    -0.57
    anthrop
    -0.57
    POSITIVE LOGITS
     +=
    1.72
     :=
    1.38
     -=
    1.33
     =
    1.32
    ++;
    1.27
    +=
    1.11
    ->
    1.09
    ();
    1.08
    =(
    1.06
    ["
    1.03
    Activations Density 0.068%

    No Known Activations