© 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. 11-RES-JB
    11. 14992
    Prev
    Next
    INDEX
    Explanations

    mentions of "UC Berkeley."

    oai_token-act-pair · gpt-3.5-turbo

    references to the University of California system and its campuses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    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
    htar
    -0.64
    ioned
    -0.63
    ã
    -0.63
     chained
    -0.62
    esthetic
    -0.62
     sights
    -0.61
     shower
    -0.59
     toile
    -0.57
    igree
    -0.57
    inger
    -0.57
    POSITIVE LOGITS
     Berkeley
    1.26
     Irvine
    1.19
    MJ
    1.07
    SC
    1.06
     Riverside
    1.02
     Davis
    1.01
    CLA
    0.97
     Asheville
    0.92
    UC
    0.91
    PD
    0.91
    Activations Density 0.047%

    No Known Activations