© 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 EvalsExportsinterp-engineNEWAPI 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. 8-RES-JB
    11. 1229
    Prev
    Next
    INDEX
    Explanations

    phrases related to universities or academic institutions

    oai_token-act-pair · gpt-3.5-turbo

    references to universities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ppings
    -0.81
    ãĥİ
    -0.66
     sheets
    -0.65
     fins
    -0.62
     bre
    -0.62
    ãĥĸ
    -0.62
     consumption
    -0.60
     vinyl
    -0.60
     sellers
    -0.60
    pecially
    -0.60
    POSITIVE LOGITS
     School
    1.10
     Libraries
    1.06
     Hospital
    1.04
     Extension
    0.97
     College
    0.95
     Students
    0.94
     Medical
    0.94
     Hosp
    0.91
     Graduate
    0.90
     Faculty
    0.90
    Activations Density 0.040%

    No Known Activations