© 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. 8-RES-JB
    11. 20360
    Prev
    Next
    INDEX
    Explanations

    words related to geometric shapes, specifically the term "square."

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "square" and its related forms in various contexts

    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
    orship
    -0.78
    uality
    -0.75
    panic
    -0.72
    audi
    -0.71
    ortium
    -0.71
    esp
    -0.70
    obal
    -0.69
    eworld
    -0.66
    bach
    -0.65
    itors
    -0.65
    POSITIVE LOGITS
     Enix
    1.29
     peg
    0.92
     metre
    0.86
     kilomet
    0.86
     mile
    0.84
     scrimmage
    0.82
     Feet
    0.80
     inch
    0.79
    lette
    0.78
    pants
    0.78
    Activations Density 0.022%

    No Known Activations