© 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. 11-RES-JB
    11. 14110
    Prev
    Next
    INDEX
    Explanations

    descriptions of mechanical modifications and enhancements to vehicles

    oai_token-act-pair · gpt-3.5-turbo

    descriptive terms related to vehicle modifications and enhancements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    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
     Manziel
    -0.80
    ebin
    -0.77
    querade
    -0.76
     largeDownload
    -0.76
     Ebola
    -0.76
    tsy
    -0.75
    advertising
    -0.75
    Screenshot
    -0.73
    Netflix
    -0.73
    cloud
    -0.72
    POSITIVE LOGITS
     brakes
    1.68
     brake
    1.68
     axle
    1.65
     tires
    1.57
     pedals
    1.53
     tyres
    1.52
     braking
    1.52
     wheels
    1.50
     tire
    1.44
     Wheels
    1.42
    Activations Density 0.278%

    No Known Activations