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. 17812
    Prev
    Next
    INDEX
    Explanations

    statistics and numerical figures within texts

    oai_token-act-pair · gpt-3.5-turbo

    numerical statistics or percentages related to various social issues

    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
     beh
    -0.65
     pandemonium
    -0.65
     appre
    -0.61
    unity
    -0.60
     suffice
    -0.58
    ihara
    -0.56
    inventoryQuantity
    -0.56
     propri
    -0.56
    xon
    -0.55
     perspect
    -0.55
    POSITIVE LOGITS
     percent
    1.30
    %
    1.26
     million
    1.07
    %-
    1.04
    pc
    1.02
     out
    1.01
    %"
    1.00
    %)
    0.93
     %
    0.92
     Percent
    0.92
    Activations Density 0.126%

    No Known Activations