© 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. 14263
    Prev
    Next
    INDEX
    Explanations

    action-related words indicating change or progress

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating future consequences 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
    ļéĨĴ
    -0.68
    leigh
    -0.67
    £ı
    -0.59
    Released
    -0.57
    mbuds
    -0.56
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.53
    aido
    -0.53
    76561
    -0.52
    oops
    -0.52
    pecially
    -0.52
    POSITIVE LOGITS
     hereafter
    1.42
     someday
    1.33
     future
    1.12
     tomorrow
    1.05
     next
    1.04
     soon
    0.95
    next
    0.89
     thereafter
    0.88
    future
    0.87
    soon
    0.87
    Activations Density 0.489%

    No Known Activations