© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 4646
    Prev
    Next
    INDEX
    Explanations

    numerical figures such as quantities and percentages

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

    quantitative descriptors and references to groups of people or entities

    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
    ocracy
    -0.67
     Witch
    -0.59
    /
    -0.58
    Rating
    -0.58
    Offline
    -0.55
    à
    -0.55
    multipl
    -0.54
    ðĿ
    -0.54
     Understanding
    -0.53
     Something
    -0.53
    POSITIVE LOGITS
     were
    1.05
     wore
    0.96
     stayed
    0.92
     weren
    0.91
     survived
    0.89
     complained
    0.88
     belonged
    0.87
     died
    0.87
     lasted
    0.84
     remained
    0.83
    Activations Density 0.210%

    No Known Activations