© 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. 11-RES-JB
    11. 14952
    Prev
    Next
    INDEX
    Explanations

    phrases related to political committees

    oai_token-act-pair · gpt-3.5-turbo

    references to governmental committees

    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
     Univers
    -0.69
    ji
    -0.68
    imm
    -0.65
    Zip
    -0.64
    éĽ
    -0.63
    ymes
    -0.62
    ku
    -0.62
    resp
    -0.61
    ulia
    -0.61
     Fountain
    -0.60
    POSITIVE LOGITS
     chair
    1.22
     hearings
    1.20
     chairman
    1.19
     chaired
    1.12
     Chair
    1.11
     Chairman
    1.07
     chairs
    1.05
    ittee
    1.03
     hearing
    1.00
     markup
    0.99
    Activations Density 0.055%

    No Known Activations