© 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. 3543
    Prev
    Next
    INDEX
    Explanations

    names of people or places described in news articles

    oai_token-act-pair · gpt-3.5-turbo

    instances of citations or references to individuals in parentheses

    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
     regret
    -0.71
     lull
    -0.70
     adjustments
    -0.69
     deem
    -0.69
     treat
    -0.67
     incre
    -0.66
     dece
    -0.65
     toll
    -0.65
     overnight
    -0.64
     skyrocket
    -0.63
    POSITIVE LOGITS
    pictured
    1.53
    left
    1.53
    Photo
    1.49
    Picture
    1.41
    center
    1.37
    Screenshot
    1.37
    bottom
    1.36
    Courtesy
    1.35
    above
    1.32
    photo
    1.31
    Activations Density 0.057%

    No Known Activations