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. 240
    Prev
    Next
    INDEX
    Explanations

    special characters or symbols in the text

    oai_token-act-pair · gpt-4-turbo

    symbols and special characters

    oai_token-act-pair · gpt-3.5-turbo

    bullet points or list items in the text

    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
    ushi
    -0.77
    omorphic
    -0.75
    brance
    -0.75
     wagon
    -0.74
    rolet
    -0.73
     grain
    -0.72
     shaping
    -0.71
    laus
    -0.71
    alsa
    -0.71
    icum
    -0.71
    POSITIVE LOGITS
    âĢ¢âĢ¢
    1.24
    âĢ¢âĢ¢âĢ¢âĢ¢
    1.13
    ï¸ı
    0.97
    ï¸
    0.92
    tal
    0.84
    âĸł
    0.78
     Includes
    0.77
    âĢ¢
    0.77
    Publisher
    0.73
    ---------
    0.71
    Activations Density 0.011%

    No Known Activations