© 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. 4-RES-JB
    11. 10568
    Prev
    Next
    INDEX
    Explanations

    phrases related to gesturing or physical actions

    oai_token-act-pair · gpt-3.5-turbo

    interaction dynamics and gestures in conversations

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

    No Comments

    Negative Logits
     administrations
    -0.75
    represented
    -0.74
     Persons
    -0.72
    gettable
    -0.71
    ¥ŀ
    -0.70
    Reviewer
    -0.70
     constituted
    -0.67
     disparate
    -0.66
     consequential
    -0.66
     unified
    -0.64
    POSITIVE LOGITS
    pause
    1.01
     angrily
    0.94
     nervously
    0.92
     grin
    0.87
     sob
    0.84
     calmly
    0.83
     shrug
    0.83
    Pause
    0.82
     softly
    0.81
     smiled
    0.81
    Activations Density 0.427%

    No Known Activations