© 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. 3-RES-JB
    11. 127
    Prev
    Next
    INDEX
    Explanations

    details related to physical actions or movements, especially involving body parts

    oai_token-act-pair · gpt-3.5-turbo

    expressions of physical trauma or injury

    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
    ocument
    -0.63
    ONSORED
    -0.56
     endorsements
    -0.55
     DACA
    -0.55
    èĢħ
    -0.54
    Financial
    -0.54
    itutional
    -0.53
    endment
    -0.53
    omics
    -0.52
     appoint
    -0.51
    POSITIVE LOGITS
     cavern
    0.65
     mound
    0.63
     edges
    0.61
     tubes
    0.61
     icy
    0.60
     protr
    0.60
     lifeless
    0.60
     gorge
    0.60
     translucent
    0.59
     cones
    0.59
    Activations Density 3.704%

    No Known Activations