© 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. 1-RES-JB
    11. 21656
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "kitten" and related terms

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the substring "itten"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    interrupted
    -0.63
    ãĥ©ãĥ³
    -0.62
    arta
    -0.62
    aceutical
    -0.61
    ifted
    -0.61
     electroly
    -0.61
    awaru
    -0.60
     lingu
    -0.59
    trans
    -0.59
     absorption
    -0.59
    POSITIVE LOGITS
    itten
    0.93
    bats
    0.90
    mast
    0.81
    enburg
    0.81
    burg
    0.80
    acht
    0.79
    berg
    0.79
    bugs
    0.76
    yard
    0.74
    hou
    0.74
    Activations Density 0.007%

    No Known Activations