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. 11-RES-JB
    6. 3254
    Prev
    Next
    INDEX
    Explanations

    numbers followed by a dash and another number representing a range

    oai_token-act-pair · gpt-3.5-turbo

    specific numerical values and their units related to products and measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     humanities
    -0.62
    ably
    -0.62
     spo
    -0.58
     Ake
    -0.57
     jung
    -0.55
     Bots
    -0.55
     Neuroscience
    -0.55
    clude
    -0.54
     unaff
    -0.53
     scholarly
    -0.53
    POSITIVE LOGITS
    mm
    1.33
     inch
    1.29
    â̳
    1.19
     gallon
    1.17
     mm
    1.15
     ounce
    1.11
    inch
    1.09
    lb
    1.07
    cm
    1.07
     watt
    1.05
    Activations Density 0.138%

    No Known Activations