© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 7-RES-JB
    11. 9592
    Prev
    Next
    INDEX
    Explanations

    mentions of political seats and elections

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DragonMagazine
    -0.81
    sonian
    -0.77
    ICLE
    -0.73
    ocrine
    -0.70
     Turtles
    -0.69
    VIDEO
    -0.68
    STD
    -0.66
    operation
    -0.65
    stic
    -0.64
     Principles
    -0.64
    POSITIVE LOGITS
    holder
    1.22
    holders
    1.18
     vacated
    1.05
     holders
    1.04
     holder
    0.89
     seats
    0.88
    marked
    0.86
    belt
    0.85
    vote
    0.85
     vacant
    0.83
    Activations Density 0.027%

    No Known Activations