© 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. 11-RES-JB
    11. 13026
    Prev
    Next
    INDEX
    Explanations

    images or pictures indicating subjects described in the accompanying text

    oai_token-act-pair · gpt-3.5-turbo

    references to photographs or images in various contexts

    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
    vor
    -0.78
    ItemTracker
    -0.78
    Few
    -0.76
    few
    -0.72
    ©¶æ¥µ
    -0.69
    uld
    -0.69
    Story
    -0.69
    sonian
    -0.69
    terness
    -0.68
    oldown
    -0.68
    POSITIVE LOGITS
     naked
    1.02
     themselves
    1.01
     yourself
    0.94
     ourselves
    0.94
     herself
    0.94
     himself
    0.93
     smiling
    0.93
     kittens
    0.93
     oneself
    0.92
     myself
    0.90
    Activations Density 0.193%

    No Known Activations