© 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. 3559
    Prev
    Next
    INDEX
    Explanations

    astronomy-related terms, including specific astronomical organizations and areas of study

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

    proper nouns and specific terminology relevant to science and technology

    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
    iculture
    -0.63
    culosis
    -0.63
     Leban
    -0.58
    ãĥĺãĥ©
    -0.57
    omsday
    -0.53
    atchewan
    -0.52
    oÄŁ
    -0.51
     severity
    -0.51
    afety
    -0.51
    ulkan
    -0.51
    POSITIVE LOGITS
    atory
    0.69
    ater
    0.63
    ate
    0.63
    ners
    0.56
    NER
    0.55
    ittees
    0.54
    els
    0.52
    ers
    0.52
     Co
    0.52
     (£
    0.51
    Activations Density 0.209%

    No Known Activations