© 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. 13123
    Prev
    Next
    INDEX
    Explanations

    dates and numerical information

    oai_token-act-pair · gpt-3.5-turbo

    dates and numerical values within the text

    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
    za
    -0.84
    zos
    -0.79
     Zucker
    -0.76
    anz
    -0.75
     Sv
    -0.74
     sands
    -0.73
     DOS
    -0.72
     Dot
    -0.72
    zi
    -0.72
     seiz
    -0.71
    POSITIVE LOGITS
    22
    1.50
    23
    1.45
     22
    1.38
     23
    1.37
    223
    1.28
     223
    1.18
    224
    1.15
    222
    1.15
    229
    1.14
    227
    1.12
    Activations Density 0.316%

    No Known Activations