© 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. 10-RES-JB
    11. 18790
    Prev
    Next
    INDEX
    Explanations

    terms related to the color "gray"

    oai_token-act-pair · gpt-3.5-turbo
    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
    ========
    -0.81
    urity
    -0.78
    ============
    -0.67
    uador
    -0.64
    iques
    -0.62
    ÄŁ
    -0.62
    etsk
    -0.62
    ique
    -0.60
    elligent
    -0.60
    igslist
    -0.60
    POSITIVE LOGITS
    hound
    1.52
    beard
    1.11
    hawk
    1.05
    hair
    0.93
    haired
    0.92
    wolf
    0.90
     Goose
    0.89
     Matter
    0.89
    idge
    0.87
    endale
    0.86
    Activations Density 0.017%

    No Known Activations