© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 12-RES-JB
    6. 4033
    Prev
    Next
    INDEX
    Explanations

    text related to social media platforms and instructions for specific activities

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

    information related to credits, specifications, and guidelines for products and projects

    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
    .")
    -0.96
    ,'"
    -0.92
    .""
    -0.90
    ',"
    -0.86
    .'"
    -0.85
    .","
    -0.84
    )."
    -0.83
    '."
    -0.83
    ."[
    -0.83
    ),"
    -0.77
    POSITIVE LOGITS
    !:
    1.01
    ?:
    0.96
    %:
    0.92
     Matters
    0.89
     Specific
    0.87
     Recommend
    0.87
     Factors
    0.85
     Differences
    0.85
     Yourself
    0.84
    ↵
    0.84
    Activations Density 1.029%

    No Known Activations