© 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. 9-RES-JB
    11. 7462
    Prev
    Next
    INDEX
    Explanations

    references to the Democratic National Committee (DNC) and Republican National Committee (RNC) in email conversations

    oai_token-act-pair · gpt-3.5-turbo

    references to the Democratic National Committee (DNC) and its officials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Kubrick
    -0.74
    ...]
    -0.74
    isu
    -0.73
    ikawa
    -0.69
    guns
    -0.68
    veh
    -0.68
    gun
    -0.67
     Oman
    -0.66
    ously
    -0.66
     Britann
    -0.65
    POSITIVE LOGITS
     Chair
    1.07
     chair
    1.03
    Leaks
    0.91
     chairman
    0.89
     staffer
    0.88
     DNC
    0.87
     Chairman
    0.86
     chairs
    0.82
     hacks
    0.79
     speeches
    0.77
    Activations Density 0.050%

    No Known Activations