© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 5831
    Prev
    Next
    INDEX
    Explanations

    references to the Democratic National Committee (DNC)

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the Democratic National Committee (DNC)

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ...]
    -0.78
    otropic
    -0.77
     Britann
    -0.73
     Shank
    -0.72
    cyl
    -0.71
    ggies
    -0.71
    perm
    -0.69
     Kubrick
    -0.68
    croft
    -0.67
    autical
    -0.67
    POSITIVE LOGITS
     DNC
    0.90
     chair
    0.88
    Leaks
    0.86
    agogue
    0.85
     Chair
    0.83
    INTON
    0.80
     treasury
    0.76
    olicy
    0.76
     staffer
    0.75
    ND
    0.72
    Activations Density 0.012%

    No Known Activations