© 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. 3301
    Prev
    Next
    INDEX
    Explanations

    mentions of social media handles

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

    mentions of the name "Kia."

    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
    ary
    -0.74
     mustache
    -0.63
    arians
    -0.63
    aneously
    -0.56
    istics
    -0.55
     disguise
    -0.55
    ized
    -0.54
    alogue
    -0.54
    aires
    -0.54
    aries
    -0.54
    POSITIVE LOGITS
    ppe
    1.35
    zza
    1.17
    pered
    1.14
    ppa
    1.13
    uthor
    1.09
    ircraft
    1.04
    ulia
    1.04
    ffe
    0.99
    BILITIES
    0.99
    ccess
    0.98
    Activations Density 0.114%

    No Known Activations