© 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. 10-RES-JB
    11. 1389
    Prev
    Next
    INDEX
    Explanations

    verbs related to physical actions, such as movement and activities

    oai_token-act-pair · gpt-3.5-turbo

    action verbs and phrases related to tasks and activities

    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
     Gamble
    -0.62
    piring
    -0.61
    CHAT
    -0.60
    ForgeModLoader
    -0.59
     Founding
    -0.57
    iHUD
    -0.56
    uga
    -0.56
    ICH
    -0.55
    bash
    -0.55
    ãĤ«
    -0.55
    POSITIVE LOGITS
     anyway
    1.44
     anyways
    1.35
     sooner
    1.30
     cautiously
    1.27
     sparing
    1.26
     responsibly
    1.22
     nonetheless
    1.21
     again
    1.20
     accordingly
    1.18
     freely
    1.17
    Activations Density 0.446%

    No Known Activations