© 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. 12666
    Prev
    Next
    INDEX
    Explanations

    currency related phrases

    oai_token-act-pair · gpt-3.5-turbo

    numerical data related to casualties or reports of violent events

    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
     eleph
    -0.79
     tremend
    -0.72
     occas
    -0.68
     newcom
    -0.68
     contemplating
    -0.66
     parting
    -0.65
    senal
    -0.61
     proport
    -0.59
     representation
    -0.59
     unnecess
    -0.59
    POSITIVE LOGITS
    Scroll
    0.87
    Egypt
    0.80
    Bus
    0.79
    ³³³
    0.79
    Prime
    0.76
    SPONSORED
    0.74
    Í
    0.74
    Britain
    0.73
    Palestinian
    0.73
    Aust
    0.73
    Activations Density 0.346%

    No Known Activations