© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 10041
    Prev
    Next
    INDEX
    Explanations

    informative or attention-grabbing words or phrases, like 'MUST WATCH'

    oai_token-act-pair · gpt-3.5-turbo

    content that relates to popular media or specific items of interest

    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
     Evans
    -0.94
     Buch
    -0.93
     Baxter
    -0.87
    Pa
    -0.86
    Brown
    -0.84
    bys
    -0.83
     Paige
    -0.83
     Iv
    -0.81
    ei
    -0.81
     Asuka
    -0.80
    POSITIVE LOGITS
     link
    1.35
     Link
    1.29
     linkage
    1.28
    link
    1.25
     tracker
    1.23
     LINK
    1.23
     trail
    1.22
    Link
    1.20
     Tracks
    1.19
    Tra
    1.17
    Activations Density 0.389%

    No Known Activations