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. 8-RES-JB
    6. 1491
    Prev
    Next
    INDEX
    Explanations

    the word "on" occurring in text

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "on."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ????????
    -0.66
    forth
    -0.60
    ean
    -0.59
    egu
    -0.59
    flies
    -0.58
    gow
    -0.57
    200000
    -0.56
    UF
    -0.56
    Bey
    -0.56
     sovere
    -0.55
    POSITIVE LOGITS
     behalf
    0.85
     Flickr
    0.82
    click
    0.79
    topic
    0.75
     Pastebin
    0.75
     Blog
    0.70
     Aging
    0.69
     Tue
    0.69
     Pinterest
    0.68
    uters
    0.67
    Activations Density 0.037%

    No Known Activations