© 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. 3-RES-JB
    11. 16150
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to conferences or formal discussions

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "con."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    terday
    -0.79
    externalActionCode
    -0.72
     Bulg
    -0.70
    ãĤ¶
    -0.69
     Beet
    -0.68
    assetsadobe
    -0.68
     Fenrir
    -0.68
    EStream
    -0.65
     Nicotine
    -0.65
     Twain
    -0.65
    POSITIVE LOGITS
    NECT
    1.19
    ventions
    1.01
    secut
    1.00
    stant
    1.00
    TERN
    0.98
    CEPT
    0.97
    clusively
    0.97
    VERT
    0.94
    CLUS
    0.93
    versely
    0.92
    Activations Density 0.005%

    No Known Activations