© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 0-RES-JB
    11. 11994
    Prev
    Next
    INDEX
    Explanations

    words related to the name "Hus" or "Harvard"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of specific university names and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Radio
    -0.73
     Tune
    -0.71
     Anti
    -0.70
     Colour
    -0.70
     Reign
    -0.64
     Torch
    -0.64
     Zar
    -0.62
     Ally
    -0.61
     Armstrong
    -0.61
     ARC
    -0.60
    POSITIVE LOGITS
    hus
    4.35
    vard
    1.51
    hu
    1.29
    vik
    1.24
    heastern
    1.22
    ensen
    1.10
    haus
    1.06
    hya
    1.03
    hair
    1.01
    hatt
    0.97
    Activations Density 0.007%

    No Known Activations