© 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 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. 10-RES-JB
    11. 3323
    Prev
    Next
    INDEX
    Explanations

    and highlight quotes from various politicians

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ulia
    -0.60
    ween
    -0.58
    ificial
    -0.57
    antics
    -0.57
    eways
    -0.57
    bees
    -0.57
    ":""},{"
    -0.56
    Kind
    -0.55
    adh
    -0.55
    Characters
    -0.55
    POSITIVE LOGITS
     Jr
    1.21
     chairman
    1.15
     Democrat
    1.10
     chair
    1.05
     Ranking
    0.94
    Republican
    0.92
     Republican
    0.91
     Chairman
    0.90
     Chair
    0.87
     lawmaker
    0.86
    Activations Density 0.095%

    No Known Activations