© 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. 8-RES-JB
    11. 10475
    Prev
    Next
    INDEX
    Explanations

    verbs related to physical movement, especially jumping and diving

    oai_token-act-pair · gpt-3.5-turbo

    actions associated with physical movement and sports-related activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    selves
    -0.78
     Monstrous
    -0.73
    aples
    -0.72
     Pione
    -0.69
    eger
    -0.68
     Fiscal
    -0.67
    vae
    -0.65
     Haram
    -0.65
     Sana
    -0.64
     Shiite
    -0.62
    POSITIVE LOGITS
    able
    1.38
    ings
    1.36
    ability
    1.27
    ables
    1.13
    ers
    1.07
    aways
    1.07
    away
    1.06
    ups
    1.06
    outs
    1.06
    athon
    1.02
    Activations Density 0.262%

    No Known Activations