© 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. 0-RES-JB
    11. 5023
    Prev
    Next
    INDEX
    Explanations

    words related to parts of the body, specifically jaws

    oai_token-act-pair · gpt-3.5-turbo

    references to jaws, both in a literal and metaphorical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    emp
    -0.72
     WRITE
    -0.68
    aiden
    -0.67
    cycle
    -0.65
    ocations
    -0.65
     Sell
    -0.64
    uca
    -0.62
     Directions
    -0.61
    per
    -0.61
    Values
    -0.60
    POSITIVE LOGITS
     jaw
    3.91
     jaws
    2.45
     eyebrow
    1.66
     Jaw
    1.65
     teeth
    1.48
     cheek
    1.40
     chin
    1.40
     mouth
    1.38
     throat
    1.32
     skull
    1.28
    Activations Density 0.014%

    No Known Activations