© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 12-RES-JB
    11. 2608
    Prev
    Next
    INDEX
    Explanations

    key phrases related to specific events or discussions, likely within a detailed context

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    key statistical or numerical data related to trends and changes over time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    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
    soType
    -0.68
     lately
    -0.66
    nesday
    -0.64
    try
    -0.64
     Sometimes
    -0.62
     Bought
    -0.61
    helps
    -0.60
     yesterday
    -0.60
    gow
    -0.60
     externalToEVAOnly
    -0.59
    POSITIVE LOGITS
     already
    0.88
     exhausted
    0.82
     totaled
    0.74
     surpassed
    0.73
    enough
    0.69
    ©¶æ¥µ
    0.68
    Already
    0.68
    apsed
    0.65
     unmist
    0.65
     ceased
    0.64
    Activations Density 0.371%

    No Known Activations