© 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. 23119
    Prev
    Next
    INDEX
    Explanations

    gestures or actions denoting communication, respect, or symbolism

    oai_token-act-pair · gpt-3.5-turbo

    references to gestures and symbolic actions

    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
    ondo
    -0.77
    elsen
    -0.71
    IED
    -0.71
    seed
    -0.70
     Nightmares
    -0.69
    ridge
    -0.68
    Mos
    -0.67
    nit
    -0.67
    raid
    -0.66
    ccording
    -0.66
    POSITIVE LOGITS
     gesture
    1.51
     gestures
    1.33
     toward
    0.94
     towards
    0.94
     dexterity
    0.88
     greeting
    0.87
     swipe
    0.81
     salute
    0.78
     recognition
    0.73
     emoji
    0.72
    Activations Density 0.039%

    No Known Activations