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. 4-RES-JB
    6. 5056
    Prev
    Next
    INDEX
    Explanations

    keywords related to programming and technical instructions

    oai_token-act-pair · gpt-3.5-turbo

    technical parameters and measurements related to programming, particularly in server and cache configurations

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

    No Comments

    Negative Logits
    uj
    -0.91
    soDeliveryDate
    -0.84
    arak
    -0.82
    dfx
    -0.78
    wcsstore
    -0.78
    ugi
    -0.76
    zek
    -0.74
    enegger
    -0.73
    chy
    -0.73
    otin
    -0.73
    POSITIVE LOGITS
    Limit
    0.91
    Sync
    0.78
     Percent
    0.74
    Counter
    0.71
    limit
    0.69
     multiplier
    0.69
     Limits
    0.68
    Offset
    0.68
     <=
    0.67
     Limit
    0.67
    Activations Density 0.115%

    No Known Activations