© 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. 5794
    Prev
    Next
    INDEX
    Explanations

    capital letters followed by words indicating specific subjects or ideas

    oai_token-act-pair · gpt-3.5-turbo

    capital letters that likely indicate significant entities or concepts

    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
     legend
    -0.89
     Apex
    -0.87
     Avenger
    -0.85
     Pegasus
    -0.85
     legendary
    -0.82
     Merry
    -0.80
     Mustang
    -0.80
     Cobra
    -0.80
     Hobbit
    -0.78
     Joker
    -0.78
    POSITIVE LOGITS
    ocusing
    1.22
    untary
    1.19
    ealing
    1.18
    idespread
    1.17
    ifting
    1.17
    apping
    1.15
    enting
    1.15
    itting
    1.13
    ailing
    1.12
    ending
    1.12
    Activations Density 0.190%

    No Known Activations