© 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. 11382
    Prev
    Next
    INDEX
    Explanations

    terms related to political topics

    oai_token-act-pair · gpt-3.5-turbo

    references to political topics and discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    imates
    -0.84
    actory
    -0.84
    uran
    -0.84
    amination
    -0.78
    ibles
    -0.70
    raction
    -0.68
    xt
    -0.68
    ossier
    -0.68
    gur
    -0.67
    val
    -0.66
    POSITIVE LOGITS
     correctness
    0.98
    hare
    0.97
    cape
    0.89
    eering
    0.86
    atism
    0.80
    manship
    0.79
     lawy
    0.77
    clinton
    0.75
    chool
    0.75
    hip
    0.74
    Activations Density 0.023%

    No Known Activations