© 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. 0-RES-JB
    11. 16341
    Prev
    Next
    INDEX
    Explanations

    seemingly random characters and sequences

    oai_token-act-pair · gpt-3.5-turbo

    special characters or symbols

    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
    verse
    -0.68
     camps
    -0.67
     Tra
    -0.67
     exhibit
    -0.66
     hypnot
    -0.66
     retrospective
    -0.65
     ze
    -0.65
     camp
    -0.64
     shares
    -0.60
     logger
    -0.60
    POSITIVE LOGITS
    ķ
    4.36
    ľ
    1.98
    Ĺ
    1.95
    ĸ
    1.85
    Ķ
    1.84
    µ
    1.84
    ĵ
    1.82
    ¢
    1.78
    Ģ
    1.78
    Ħ
    1.77
    Activations Density 0.013%

    No Known Activations