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. 4-RES-JB
    6. 17811
    Prev
    Next
    INDEX
    Explanations

    the phrase "pretty much"

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "pretty much" in various contexts

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

    No Comments

    Negative Logits
    etts
    -0.78
    andra
    -0.78
    atures
    -0.77
    oresc
    -0.75
     Cosponsors
    -0.75
    emen
    -0.75
    iem
    -0.69
    abad
    -0.68
    BW
    -0.68
    ves
    -0.68
    POSITIVE LOGITS
     nailed
    0.73
     boils
    0.69
     unus
    0.68
     useless
    0.68
     worthless
    0.65
     unint
    0.65
     nil
    0.65
    QUIRE
    0.64
     lifeless
    0.64
     illiter
    0.63
    Activations Density 0.017%

    No Known Activations