© 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. 7677
    Prev
    Next
    INDEX
    Explanations

    words related to taking actions or making decisions

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "acted" in various contexts

    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
     Num
    -0.63
     #
    -0.62
     comparison
    -0.58
    onomic
    -0.57
     site
    -0.57
     mailing
    -0.57
     relegation
    -0.57
    bar
    -0.56
     Maple
    -0.56
     branding
    -0.55
    POSITIVE LOGITS
     acted
    3.49
     behaved
    2.03
    acted
    1.78
     act
    1.60
     interacted
    1.59
     acting
    1.58
     reacted
    1.55
     intervened
    1.52
     acts
    1.45
     interfered
    1.44
    Activations Density 0.011%

    No Known Activations