© 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. 6187
    Prev
    Next
    INDEX
    Explanations

    currency symbols

    oai_token-act-pair · gpt-3.5-turbo

    references to time-related activities or breaks

    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
    umen
    -0.83
     1920
    -0.69
     1280
    -0.65
    ascript
    -0.61
     retard
    -0.59
     helium
    -0.59
    1920
    -0.57
    UES
    -0.57
     1880
    -0.57
     960
    -0.57
    POSITIVE LOGITS
    3
    1.31
     3
    1.16
     THREE
    0.94
     Third
    0.93
    three
    0.91
    thirds
    0.89
    333
    0.88
     III
    0.88
    Third
    0.85
    third
    0.84
    Activations Density 0.179%

    No Known Activations