© 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. 2809
    Prev
    Next
    INDEX
    Explanations

    words related to physical force and action, such as penetrating, swinging, biting, and damaging

    oai_token-act-pair · gpt-3.5-turbo

    actions that involve forceful movement or penetration

    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
    ruary
    -0.88
    DragonMagazine
    -0.78
     Nationwide
    -0.71
    show
    -0.71
     Trend
    -0.70
    utan
    -0.70
    ãĤ´ãĥ³
    -0.69
     Commentary
    -0.69
    ————————————————
    -0.67
    otide
    -0.67
    POSITIVE LOGITS
     surfaces
    1.52
     objects
    1.50
     walls
    1.37
     targets
    1.32
     obstacles
    1.29
     buildings
    1.28
     ceilings
    1.28
     roofs
    1.26
     enemies
    1.21
     foes
    1.20
    Activations Density 0.321%

    No Known Activations