© 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. 11-RES-JB
    11. 7451
    Prev
    Next
    INDEX
    Explanations

    instances of the word 'then' followed by numbers

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "then."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    toe
    -0.71
    ones
    -0.58
    monds
    -0.58
     Parables
    -0.57
     Hayden
    -0.56
     EntityItem
    -0.56
     Vand
    -0.55
    chu
    -0.54
    ting
    -0.54
     Achievement
    -0.54
    POSITIVE LOGITS
     proceeded
    1.11
    DragonMagazine
    0.76
    orbit
    0.76
    -'
    0.76
    -,
    0.74
     proceeds
    0.71
    arily
    0.71
    vernment
    0.71
     proceed
    0.69
     ensued
    0.69
    Activations Density 0.047%

    No Known Activations