© 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. 10-RES-JB
    11. 11218
    Prev
    Next
    INDEX
    Explanations

    mentions of the institution "Stanford"

    oai_token-act-pair · gpt-3.5-turbo

    references to Stanford University

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hops
    -0.75
    Sov
    -0.74
    erate
    -0.71
    bleacher
    -0.64
    erous
    -0.63
    alez
    -0.63
     stuffing
    -0.63
    usher
    -0.62
    DonaldTrump
    -0.61
    qs
    -0.61
    POSITIVE LOGITS
     University
    1.06
     Institution
    1.01
     Cardinal
    0.89
     Encyclopedia
    0.86
     Graduate
    0.84
     Prison
    0.82
     Univ
    0.80
     Hills
    0.79
    sburg
    0.79
     Linear
    0.78
    Activations Density 0.036%

    No Known Activations