© 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 EvalsExportsAPI 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. 7-RES-JB
    11. 23985
    Prev
    Next
    INDEX
    Explanations

    places or locations with 'de' in the name

    oai_token-act-pair · gpt-3.5-turbo

    the preposition "de" indicating possession or relation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uyomi
    -0.82
    ilial
    -0.80
    ippy
    -0.73
    aceous
    -0.72
     Wage
    -0.71
    DragonMagazine
    -0.70
    ambers
    -0.69
    krit
    -0.69
    ancial
    -0.69
     Flavoring
    -0.68
    POSITIVE LOGITS
    utsche
    1.09
    cember
    1.06
     la
    1.00
    arest
    0.95
    utsch
    0.92
     los
    0.90
    uces
    0.89
    bris
    0.87
     Blasio
    0.87
     jour
    0.85
    Activations Density 0.020%

    No Known Activations