© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 0-RES-JB
    11. 14748
    Prev
    Next
    INDEX
    Explanations

    Japanese characters

    oai_token-act-pair · gpt-3.5-turbo

    specific encoded symbols or characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Mole
    -0.71
     Faw
    -0.67
     Bates
    -0.65
    aiman
    -0.64
     Seller
    -0.62
    phant
    -0.62
     Estimates
    -0.61
     Physicians
    -0.60
    atus
    -0.60
    kefeller
    -0.60
    POSITIVE LOGITS
    æĿ
    0.98
     either
    0.87
     him
    0.77
    à
    0.69
    edo
    0.68
    Mot
    0.66
    either
    0.66
     footing
    0.66
    him
    0.65
     oneself
    0.62
    Activations Density 0.000%

    No Known Activations