© 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. 8-RES-JB
    11. 1123
    Prev
    Next
    INDEX
    Explanations

    programming-related terms and messages, including JavaScript enabled, syntax error warnings, and HTML5 capability

    oai_token-act-pair · gpt-3.5-turbo

    references to programming languages and errors associated with them

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nen
    -0.66
    icip
    -0.65
    ESA
    -0.63
    icipated
    -0.63
    pload
    -0.60
    jri
    -0.59
    ?????-
    -0.59
    EStreamFrame
    -0.58
    secut
    -0.58
    iless
    -0.57
    POSITIVE LOGITS
     converter
    0.65
     Wilde
    0.58
    Magikarp
    0.57
     mustache
    0.55
     underpin
    0.54
     suited
    0.53
     Faust
    0.52
     liner
    0.52
     Pyro
    0.51
     chops
    0.51
    Activations Density 1.220%

    No Known Activations