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. 3-RES-JB
    6. 2367
    Prev
    Next
    INDEX
    Explanations

    words related to positions or titles like "President," "Commission," "Chairman," and "Magistrates."

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "or" in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     msec
    -0.71
    eas
    -0.62
    £ı
    -0.59
     rounded
    -0.58
    inctions
    -0.57
     {{
    -0.57
    Fra
    -0.56
    Alert
    -0.56
    lished
    -0.56
    ¥ŀ
    -0.56
    POSITIVE LOGITS
    ific
    1.09
    andom
    1.07
    chid
    1.05
    phans
    0.96
    ikawa
    0.93
    onto
    0.92
    acial
    0.92
    ussia
    0.92
    izons
    0.91
    thodox
    0.87
    Activations Density 0.038%

    No Known Activations