© 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. 1-RES-JB
    11. 14333
    Prev
    Next
    INDEX
    Explanations

    specific mentions of titles

    oai_token-act-pair · gpt-3.5-turbo

    repeated mentions of the word "titles" in contexts related to media or entertainment

    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
    ITH
    -0.75
    gm
    -0.71
    ndum
    -0.70
     Alto
    -0.65
     Rasmussen
    -0.62
     SS
    -0.61
     Tucker
    -0.61
     intestine
    -0.61
     Common
    -0.59
     Hoffman
    -0.59
    POSITIVE LOGITS
     titles
    1.28
    manship
    1.00
    title
    0.93
    marks
    0.90
    paces
    0.86
     title
    0.84
    itles
    0.84
    ãĥĩ
    0.80
    ¥µ
    0.79
    Hunt
    0.79
    Activations Density 0.011%

    No Known Activations