© 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 EvalsExportsinterp-engineNEWAPI 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. 11664
    Prev
    Next
    INDEX
    Explanations

    mentions of political events and predictions, specifically related to election outcomes

    oai_token-act-pair · gpt-3.5-turbo

    repeated mentions of "the" and references to the Republican Party

    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
    rete
    -0.85
    SPONSORED
    -0.79
    isi
    -0.72
    bek
    -0.71
    inces
    -0.69
    hend
    -0.69
     served
    -0.68
    ESPN
    -0.67
     accordingly
    -0.67
    gru
    -0.66
    POSITIVE LOGITS
     presidency
    1.15
     hearts
    1.10
     coveted
    1.08
     mantle
    1.08
     reins
    1.08
     entirety
    1.03
     slightest
    1.02
     throne
    1.01
     largest
    0.98
     same
    0.98
    Activations Density 0.162%

    No Known Activations