© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 10-RES-JB
    11. 8392
    Prev
    Next
    INDEX
    Explanations

    contractions of "could not"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "couldn't."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    senal
    -0.73
    ccording
    -0.71
     challeng
    -0.65
     populated
    -0.64
     guided
    -0.64
     revolving
    -0.62
     gobl
    -0.62
     Published
    -0.61
     phased
    -0.61
    anwhile
    -0.61
    POSITIVE LOGITS
    't
    1.80
    ´
    0.92
    ÃŃ
    0.90
    fortunately
    0.89
    itely
    0.89
    unn
    0.83
    NOT
    0.82
    aden
    0.79
    usually
    0.77
    Western
    0.76
    Activations Density 0.021%

    No Known Activations