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. 10918
    Prev
    Next
    INDEX
    Explanations

    terms related to processes or procedures

    oai_token-act-pair · gpt-3.5-turbo

    mentions of various processes

    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
    friends
    -0.80
    wings
    -0.78
    obar
    -0.78
    wich
    -0.73
    pants
    -0.72
    landers
    -0.72
    bane
    -0.72
    bucks
    -0.70
    jew
    -0.70
    stars
    -0.69
    POSITIVE LOGITS
     process
    3.81
     processes
    2.69
     Process
    2.59
    process
    2.42
     procedure
    1.98
    Process
    1.70
     PROC
    1.56
     mechanism
    1.44
     procedures
    1.36
     processing
    1.32
    Activations Density 0.031%

    No Known Activations