© 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. 11-RES-JB
    11. 20881
    Prev
    Next
    INDEX
    Explanations

    numbers with or without special symbols

    oai_token-act-pair · gpt-3.5-turbo

    instances of the letter 'l'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥ¼ãĥĨãĤ£
    -0.69
     havoc
    -0.64
     spirited
    -0.63
     fund
    -0.62
     BART
    -0.62
     Satanic
    -0.61
     Vald
    -0.59
     Labor
    -0.59
     Lit
    -0.58
     household
    -0.57
    POSITIVE LOGITS
    aptop
    1.48
    ongevity
    1.37
    ocated
    1.36
    ayers
    1.35
    ifestyle
    1.34
    anguages
    1.34
    ateral
    1.30
    ibraries
    1.29
    ounge
    1.26
    ubric
    1.26
    Activations Density 0.033%

    No Known Activations