© 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. 6-RES-JB
    11. 13854
    Prev
    Next
    INDEX
    Explanations

    instances where the word "sitting" is used in a document

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "sitting"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iler
    -0.92
    ilers
    -0.80
    raid
    -0.75
    iction
    -0.72
    usable
    -0.69
    ctr
    -0.67
    xual
    -0.64
    ractical
    -0.63
    enforcement
    -0.63
    effective
    -0.62
    POSITIVE LOGITS
     ducks
    0.87
    uate
    0.86
    aution
    0.85
     atop
    0.82
     seiz
    0.80
    entary
    0.78
    lie
    0.76
    uations
    0.74
    âĸ¬
    0.73
    ivas
    0.73
    Activations Density 0.024%

    No Known Activations