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. 1-RES-JB
    6. 6223
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "on"

    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 @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ĥª
    -0.95
    è¦ļéĨĴ
    -0.88
    ħĭ
    -0.75
    DIR
    -0.72
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.72
     actionGroup
    -0.72
    æĸ¹
    -0.71
     à¨
    -0.70
    BIP
    -0.70
    ACTED
    -0.68
    POSITIVE LOGITS
    etheless
    1.33
    on
    1.04
    coming
    1.01
    auts
    1.01
    essee
    0.98
    terday
    0.95
    arios
    0.93
    stadt
    0.92
    osuke
    0.91
    ons
    0.90
    Activations Density 0.032%

    No Known Activations