© 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. 12-RES-JB
    11. 2650
    Prev
    Next
    INDEX
    Explanations

    technical specifications or details about electronic devices

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    instances of the word "know" and its variations, indicating knowledge or awareness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    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
    ĪĴ
    -0.80
    itter
    -0.74
    Ħ¢
    -0.72
    ishers
    -0.68
    IRO
    -0.67
     Instr
    -0.67
    ishable
    -0.65
    ŃĶ
    -0.63
    anmar
    -0.62
    uel
    -0.61
    POSITIVE LOGITS
     anecd
    1.03
     intimately
    1.01
    ledge
    0.97
    lege
    0.95
     about
    0.92
     existed
    0.89
     exists
    0.86
     instinctively
    0.84
     nothing
    0.82
     beforehand
    0.78
    Activations Density 0.102%

    No Known Activations