© 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. 9-RES-JB
    11. 14733
    Prev
    Next
    INDEX
    Explanations

    mentions of the university "Columbia"

    oai_token-act-pair · gpt-3.5-turbo

    references to Columbia University

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    chers
    -0.78
    cher
    -0.77
    esthetic
    -0.74
    nesses
    -0.70
    hered
    -0.70
    req
    -0.68
    visor
    -0.67
    olkien
    -0.66
    ende
    -0.65
    endo
    -0.65
    POSITIVE LOGITS
     Pictures
    1.01
     Heights
    1.00
     Journalism
    0.88
     River
    0.87
     Gorge
    0.84
     Broadcasting
    0.83
     Pike
    0.81
     Crew
    0.78
     Canal
    0.74
     Colleges
    0.74
    Activations Density 0.059%

    No Known Activations