© 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. 11401
    Prev
    Next
    INDEX
    Explanations

    dates and numerical values structured in a specific way

    oai_token-act-pair · gpt-3.5-turbo

    terms related to classifications and categories within various contexts

    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
    Wan
    -0.90
    mosp
    -0.89
    hire
    -0.84
    Kick
    -0.81
     Peng
    -0.77
    Mir
    -0.77
    ffe
    -0.76
     Wellington
    -0.73
     Faith
    -0.73
    Lee
    -0.71
    POSITIVE LOGITS
     classification
    2.08
     category
    1.89
     categories
    1.86
     categor
    1.81
     classify
    1.78
     Classification
    1.62
     Categories
    1.58
    Category
    1.54
     subclass
    1.54
     Category
    1.53
    Activations Density 0.400%

    No Known Activations