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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 10-RES-JB
    6. 2442
    Prev
    Next
    INDEX
    Explanations

    negative emotions or actions such as neglect, contempt, disdain, and scorn

    oai_token-act-pair · gpt-3.5-turbo

    negative sentiments related to neglect and contempt

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     misunder
    -0.63
     helicop
    -0.61
     Mehran
    -0.59
     livest
    -0.58
     TIT
    -0.58
    >>>>>>>>
    -0.58
     anecd
    -0.57
     skating
    -0.57
     toget
    -0.57
     Kurd
    -0.56
    POSITIVE LOGITS
    ful
    2.65
    fully
    2.33
    FUL
    1.80
    fulness
    1.78
    full
    1.55
    ible
    1.46
    eful
    1.32
    iful
    1.31
    uously
    1.30
    ingly
    1.28
    Activations Density 0.103%

    No Known Activations