Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 12-RES-JB
    6. 15241
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals and institutions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    references to individuals or organizations involved in news reporting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    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
    ."[
    -0.89
    ).[
    -0.84
    ©¶æ
    -0.84
    tymology
    -0.79
    ibliography
    -0.77
     coerc
    -0.75
     pse
    -0.73
    ".[
    -0.72
    foundland
    -0.72
    endum
    -0.70
    POSITIVE LOGITS
     USA
    1.15
     Buzz
    1.00
     Video
    0.91
     STA
    0.89
    CLOSE
    0.87
     VIDEOS
    0.86
    dayName
    0.80
     az
    0.79
    Buy
    0.79
    USA
    0.79
    Activations Density 0.055%

    No Known Activations