© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 2815
    Prev
    Next
    INDEX
    Explanations

    phrases containing the word "demanding"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "that" indicating demands or requirements

    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
     Geological
    -0.62
     Pose
    -0.59
     Thousand
    -0.58
    ãĥ¬
    -0.58
     Antar
    -0.57
     Ups
    -0.57
    ãĥ¡
    -0.57
     Thur
    -0.57
     Sapp
    -0.56
    thro
    -0.56
    POSITIVE LOGITS
    cher
    0.78
    chers
    0.72
     nomine
    0.71
    eday
    0.70
    iquid
    0.65
     pesky
    0.65
    soever
    0.65
    ividual
    0.64
    milo
    0.64
    BIL
    0.63
    Activations Density 0.191%

    No Known Activations