© 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. 0-RES-JB
    11. 18278
    Prev
    Next
    INDEX
    Explanations

    words related to physical actions or activities

    oai_token-act-pair · gpt-3.5-turbo

    references to specific actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aunder
    -0.69
    wn
    -0.68
    ologies
    -0.61
    Pand
    -0.61
     dehyd
    -0.60
    erved
    -0.60
    ghan
    -0.60
    yss
    -0.60
    bek
    -0.59
    aund
    -0.58
    POSITIVE LOGITS
     action
    3.86
     Action
    2.63
     ACTION
    2.56
    Action
    2.26
    action
    2.21
     actions
    2.19
     Actions
    1.88
     inaction
    1.60
     ACTIONS
    1.47
    ACTION
    1.42
    Activations Density 0.016%

    No Known Activations