© 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. 11-RES-JB
    11. 21057
    Prev
    Next
    INDEX
    Explanations

    single words that seem to stand out or are highlighted in some way

    oai_token-act-pair · gpt-3.5-turbo

    verbs and adjectives related to physical states or changes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_pre
    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_pre
    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
     Week
    -0.60
     [|
    -0.57
     Jiu
    -0.57
     Korea
    -0.56
     professionally
    -0.54
    ovember
    -0.53
    ;;;;
    -0.51
     Rica
    -0.51
     Lanka
    -0.51
     Leone
    -0.51
    POSITIVE LOGITS
    iest
    1.10
    liest
    1.06
    cients
    0.99
     portion
    0.93
    eness
    0.92
    ppings
    0.92
    hest
    0.88
    ultimate
    0.82
     aspect
    0.81
    osphere
    0.81
    Activations Density 0.558%

    No Known Activations