Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 16233
    Prev
    Next
    INDEX
    Explanations

    words related to equipment or being equipped

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "equipped" 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
     Origin
    -0.68
    row
    -0.64
     fav
    -0.63
     Vince
    -0.63
     Calls
    -0.60
     bitterness
    -0.60
     Barry
    -0.60
     Corey
    -0.59
     Sugar
    -0.59
    votes
    -0.59
    POSITIVE LOGITS
     equipped
    3.60
    equipped
    2.59
     equip
    2.06
     fitted
    1.73
     stocked
    1.65
    fitted
    1.55
     configured
    1.52
     staffed
    1.44
     endowed
    1.39
     furnished
    1.38
    Activations Density 0.020%

    No Known Activations