© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 22253
    Prev
    Next
    INDEX
    Explanations

    phrases that start with "For"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "For" used to introduce various topics or sections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    LAB
    -0.69
    LINE
    -0.64
     ()
    -0.61
     floated
    -0.60
     singled
    -0.59
    ickey
    -0.59
     constitu
    -0.58
    itiz
    -0.57
     (),
    -0.57
    ,.
    -0.56
    POSITIVE LOGITS
    gotten
    1.54
    bidden
    1.42
    give
    1.26
    get
    1.26
    bes
    1.25
    ced
    1.22
    got
    1.18
    um
    1.14
    ums
    1.14
    cing
    1.11
    Activations Density 0.055%

    No Known Activations