© 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. 4699
    Prev
    Next
    INDEX
    Explanations

    names of editors

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

    mentions of editors and editorial roles in media contexts

    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
    enegger
    -0.63
    aband
    -0.62
    aders
    -0.58
    ulus
    -0.58
    theless
    -0.58
     steam
    -0.57
    assium
    -0.57
     Confederation
    -0.57
    alsa
    -0.55
    ulia
    -0.54
    POSITIVE LOGITS
    ials
    1.72
    ially
    1.39
    ial
    1.08
    iate
    0.84
    iola
    0.76
    hips
    0.71
    IAL
    0.71
    furt
    0.70
     Editorial
    0.70
     emer
    0.69
    Activations Density 0.060%

    No Known Activations