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. 8-RES-JB
    6. 8794
    Prev
    Next
    INDEX
    Explanations

    phrases or sentences describing the action of waving

    oai_token-act-pair · gpt-3.5-turbo

    the action of waving or related gestures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    unker
    -0.72
     Forced
    -0.72
    CLUS
    -0.70
     defic
    -0.69
    Ranked
    -0.68
    pton
    -0.67
    д
    -0.66
     commute
    -0.66
    issions
    -0.64
    MAT
    -0.64
    POSITIVE LOGITS
     fingers
    1.02
     palms
    1.02
    lasses
    0.98
     shoulders
    0.91
    stretched
    0.91
     goodbye
    0.89
     palm
    0.87
     thumbs
    0.86
     gestures
    0.84
     gesture
    0.84
    Activations Density 0.122%

    No Known Activations