© 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. 6-RES-JB
    11. 8459
    Prev
    Next
    INDEX
    Explanations

    mentions of institutions like Johns Hopkins University

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific universities and individuals associated with them

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mble
    -0.81
    tto
    -0.80
    trap
    -0.67
    Spread
    -0.65
    anza
    -0.63
    wreck
    -0.62
    ment
    -0.62
    charg
    -0.62
    lier
    -0.61
    liest
    -0.61
    POSITIVE LOGITS
     Hopkins
    1.01
    istry
    0.96
    sonian
    0.86
     Johns
    0.85
    insula
    0.84
    imore
    0.83
    otom
    0.83
    ons
    0.81
    arton
    0.80
    omen
    0.77
    Activations Density 0.029%

    No Known Activations