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. 2-RES-JB
    6. 1107
    Prev
    Next
    INDEX
    Explanations

    the word "gonna" which is a colloquial contraction for "going to."

    oai_token-act-pair · gpt-3.5-turbo

    the colloquial phrase "gonna" indicating future intention or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mere
    -0.81
    hips
    -0.76
    lain
    -0.75
    template
    -0.74
    controlled
    -0.73
    operated
    -0.73
    icipated
    -0.71
    Newsletter
    -0.71
    lying
    -0.69
    ace
    -0.69
    POSITIVE LOGITS
     gonna
    0.90
     wanna
    0.88
     give
    0.86
     be
    0.82
     tha
    0.82
     get
    0.80
     snag
    0.79
     shove
    0.78
     try
    0.76
     buckle
    0.76
    Activations Density 0.005%

    No Known Activations