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. 7-RES-JB
    6. 13272
    Prev
    Next
    INDEX
    Explanations

    legal terms or actions related to lawsuits

    oai_token-act-pair · gpt-3.5-turbo

    words related to illegality or criminality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    yip
    -0.68
     Kahn
    -0.63
    manship
    -0.59
     Feast
    -0.58
    ©¶æ
    -0.58
    hner
    -0.57
    chini
    -0.57
    RESULTS
    -0.56
    itiveness
    -0.56
    VALUE
    -0.55
    POSITIVE LOGITS
    ãĤ¼ãĤ¦ãĤ¹
    0.72
     feder
    0.65
    airo
    0.64
    rane
    0.63
     womb
    0.62
    estine
    0.62
    ãĥī
    0.62
    au
    0.61
    asonic
    0.61
    romeda
    0.60
    Activations Density 0.282%

    No Known Activations