© 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. 0-RES-JB
    11. 9940
    Prev
    Next
    INDEX
    Explanations

    names related to a particular individual - "Dem"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the Democratic Party

    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
     processors
    -0.72
     paddle
    -0.72
    othe
    -0.69
     circuits
    -0.69
    atson
    -0.69
     BCC
    -0.69
    fw
    -0.69
    olkien
    -0.69
    oots
    -0.66
    olson
    -0.65
    POSITIVE LOGITS
     Dem
    3.81
    Dem
    2.56
    dem
    2.21
     DEM
    1.90
     dem
    1.87
     Dems
    1.77
    DEM
    1.46
     Demo
    1.43
     Dempsey
    1.18
     Des
    1.14
    Activations Density 0.022%

    No Known Activations