© 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. 4677
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal or political events and discussions

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

    referenced trends and statistics that indicate significant patterns or outcomes in various 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
     guiActiveUn
    -0.97
    obyl
    -0.88
    ãĥĥãĥĪ
    -0.88
    ãĤ´ãĥ³
    -0.88
    icter
    -0.86
    ailability
    -0.86
    ÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤ
    -0.85
     exting
    -0.85
    ÃĥÃĤ
    -0.84
    -0.84
    POSITIVE LOGITS
     telev
    0.60
     TVs
    0.60
     grocery
    0.59
     TV
    0.59
     dining
    0.58
     restaurants
    0.58
     stadium
    0.58
     speakers
    0.57
     cards
    0.57
     restaurant
    0.57
    Activations Density 1.890%

    No Known Activations