© 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. 7-RES-JB
    11. 2309
    Prev
    Next
    INDEX
    Explanations

    actions related to waving or indicating through hand gestures

    oai_token-act-pair · gpt-3.5-turbo

    actions related to waving or signaling

    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
     defic
    -0.72
    ãĥ¯ãĥ³
    -0.71
    unker
    -0.70
    Ranked
    -0.68
    д
    -0.67
     Colleges
    -0.63
    igne
    -0.62
     Forced
    -0.60
    ãĤ·ãĥ£
    -0.58
    ESS
    -0.58
    POSITIVE LOGITS
     goodbye
    1.19
    lasses
    0.96
     hello
    0.85
     waving
    0.82
    uay
    0.79
    wheel
    0.79
    chairs
    0.77
     waved
    0.77
     torches
    0.76
     frantically
    0.76
    Activations Density 0.027%

    No Known Activations