© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 2366
    Prev
    Next
    INDEX
    Explanations

    quotes expressing strong affirmation or determination

    oai_token-act-pair · gpt-3.5-turbo
    Triggered by @bot

    expressions of political sentiment or assertion

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    ELY
    -0.77
    istically
    -0.71
    ethe
    -0.70
    GET
    -0.69
    gravity
    -0.67
    epad
    -0.66
    bes
    -0.65
    arton
    -0.65
    found
    -0.64
    bet
    -0.64
    POSITIVE LOGITS
     Parties
    0.73
     NETWORK
    0.71
     Maduro
    0.62
     Abram
    0.58
     Framework
    0.58
    terday
    0.57
     Nikki
    0.56
     [|
    0.56
    umar
    0.56
     Dems
    0.55
    Activations Density 0.149%

    No Known Activations