© 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. 10-RES-JB
    11. 4589
    Prev
    Next
    INDEX
    Explanations

    names of individuals or entities

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the letter "f" in the text

    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
     paraly
    -0.62
    IU
    -0.57
    Answer
    -0.57
     Passenger
    -0.56
     terminal
    -0.55
     Scorp
    -0.55
     fetal
    -0.54
     Boone
    -0.53
     wrench
    -0.52
     strategically
    -0.52
    POSITIVE LOGITS
    ornia
    1.10
    ruits
    1.02
    rost
    1.01
    ication
    1.01
    ilipp
    0.99
    rance
    0.99
    efe
    0.98
    iltration
    0.98
    usion
    0.98
    ritz
    0.97
    Activations Density 0.042%

    No Known Activations