© 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. 4614
    Prev
    Next
    INDEX
    Explanations

    phrases related to social issues and controversies

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

    words related to sexual behaviors and societal dynamics

    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
     clar
    -0.70
     downs
    -0.70
     Pieces
    -0.69
     surprises
    -0.69
     stops
    -0.68
     cracking
    -0.66
     shocks
    -0.65
     ups
    -0.65
     stabil
    -0.65
     cracks
    -0.64
    POSITIVE LOGITS
    igrate
    1.23
    have
    1.12
    rive
    1.07
    ailed
    1.06
    itate
    1.06
    igrated
    1.05
    inate
    1.04
    pire
    1.04
    iate
    1.02
    are
    1.02
    Activations Density 0.177%

    No Known Activations