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. 805
    Prev
    Next
    INDEX
    Explanations

    phrases containing the word "sat"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "sat."

    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
    API
    -0.75
    scene
    -0.74
     MIS
    -0.74
    emaker
    -0.70
    hots
    -0.68
    ources
    -0.68
    Maker
    -0.68
    source
    -0.68
    worthiness
    -0.67
     guiName
    -0.67
    POSITIVE LOGITS
     sat
    3.62
    sat
    2.14
     sit
    1.74
     Sat
    1.72
     sits
    1.66
    Sat
    1.60
     sitting
    1.40
     stood
    1.33
     seated
    1.21
     stared
    1.15
    Activations Density 0.008%

    No Known Activations