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. 0-RES-JB
    6. 7048
    Prev
    Next
    INDEX
    Explanations

    specific numerical values (e.g., quantities or measurements)

    oai_token-act-pair · gpt-3.5-turbo

    instances of specific numerical values in the text, particularly those related to quantities or measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •Embedding Space Digit Features

    No Comments

    Negative Logits
     Runtime
    -0.69
     Brennan
    -0.69
     Blake
    -0.68
    oping
    -0.68
     Riley
    -0.68
    ni
    -0.67
     idol
    -0.66
     OC
    -0.65
     imperson
    -0.65
     Yang
    -0.64
    POSITIVE LOGITS
    150
    2.92
     150
    2.19
    1500
    1.66
    130
    1.62
    450
    1.54
     1500
    1.54
    250
    1.52
    550
    1.47
    110
    1.45
    350
    1.45
    Activations Density 0.019%

    No Known Activations