© 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. 9-RES-JB
    11. 2267
    Prev
    Next
    INDEX
    Explanations

    file extensions and URLs

    oai_token-act-pair · gpt-3.5-turbo

    image file extensions and related metadata

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    verning
    -0.76
     veter
    -0.74
    hani
    -0.73
     ment
    -0.71
     principals
    -0.71
    idelines
    -0.71
    ixir
    -0.70
    gaard
    -0.70
     pronouns
    -0.70
     lect
    -0.70
    POSITIVE LOGITS
    jpg
    1.14
     Mehran
    1.10
    png
    1.01
    crop
    0.94
    img
    0.94
    "}
    0.91
    AAAAAAAA
    0.87
    uploads
    0.85
    "></
    0.84
     Upload
    0.83
    Activations Density 0.045%

    No Known Activations