© 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. 12-RES-JB
    11. 3271
    Prev
    Next
    INDEX
    Explanations

    contact information

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    contact information and mentions of communication methods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     fronts
    -0.65
     forefront
    -0.59
    \":
    -0.54
     Mane
    -0.54
     canonical
    -0.53
     possibilities
    -0.52
     helm
    -0.52
     possibility
    -0.52
     tack
    -0.51
     gears
    -0.51
    POSITIVE LOGITS
    ById
    0.92
     pione
    0.90
     toll
    0.83
    scribe
    0.76
    =-=-=-=-
    0.75
     via
    0.75
    uilding
    0.70
     securely
    0.69
    bernatorial
    0.68
     electronically
    0.67
    Activations Density 0.100%

    No Known Activations