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. 17314
    Prev
    Next
    INDEX
    Explanations

    terms related to the word "chief"

    oai_token-act-pair · gpt-3.5-turbo

    repeated mentions of the word "chie."

    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
     thunder
    -0.64
     trailers
    -0.62
     inflammation
    -0.62
     basil
    -0.61
     samples
    -0.60
     Thunder
    -0.59
     shipping
    -0.59
     latex
    -0.58
     flooding
    -0.57
    OIL
    -0.57
    POSITIVE LOGITS
    chie
    4.80
    chieve
    1.60
    cknowled
    1.31
    chy
    1.22
    cknow
    1.15
    jah
    1.14
    cher
    1.13
    zie
    1.10
     achie
    1.08
    ches
    1.07
    Activations Density 0.012%

    No Known Activations