© 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. 3768
    Prev
    Next
    INDEX
    Explanations

    terms related to political figures and appointments

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

    instances of the word "term" and its variations, often related to political positions or appointments

    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
    riad
    -0.63
     Veh
    -0.59
    uve
    -0.57
    zo
    -0.56
     Towns
    -0.56
    otle
    -0.55
    rotein
    -0.54
     Tart
    -0.54
    ORY
    -0.54
     choir
    -0.54
    POSITIVE LOGITS
    ites
    1.09
    ite
    0.95
     coined
    0.88
    soDeliveryDate
    0.84
    lock
    0.83
    icides
    0.81
    azine
    0.80
    icide
    0.79
     limits
    0.77
    paces
    0.76
    Activations Density 0.040%

    No Known Activations