© 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. 2628
    Prev
    Next
    INDEX
    Explanations

    acronyms related to international organizations

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

    mentions of NATO and its relevance in global discussions

    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
    land
    -0.73
    tro
    -0.73
    odor
    -0.70
    ido
    -0.68
    inch
    -0.67
    ads
    -0.66
    cker
    -0.66
    atha
    -0.65
    ila
    -0.64
    ftime
    -0.63
    POSITIVE LOGITS
    chell
    0.64
    Ò
    0.59
    OME
    0.58
    IFIC
    0.58
    IENT
    0.58
    e
    0.57
    I
    0.56
     Scrib
    0.56
    EMENT
    0.54
    eur
    0.54
    Activations Density 0.129%

    No Known Activations