© 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. 3-RES-JB
    11. 4610
    Prev
    Next
    INDEX
    Explanations

    special characters with specific patterns

    oai_token-act-pair · gpt-3.5-turbo

    prominent and recurring terms, particularly related to evaluations or categorizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     credits
    -0.67
     chart
    -0.64
     styles
    -0.63
     exact
    -0.60
     landmarks
    -0.60
     diplom
    -0.58
     handic
    -0.57
     affili
    -0.57
     span
    -0.57
     accord
    -0.57
    POSITIVE LOGITS
    grass
    0.85
    ingly
    0.79
    hest
    0.76
    thens
    0.74
    esh
    0.73
    rup
    0.72
    ify
    0.71
    ified
    0.70
    itivity
    0.70
    atoon
    0.70
    Activations Density 0.221%

    No Known Activations