© 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 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. 4673
    Prev
    Next
    INDEX
    Explanations

    names of political leaders

    oai_token-act-pair · gpt-3.5-turbo

    references to political leaders and their actions

    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
    amins
    -0.79
    estones
    -0.76
    acters
    -0.70
    rawdownloadcloneembedreportprint
    -0.68
     caul
    -0.67
     interpol
    -0.66
     NCT
    -0.66
    Michigan
    -0.65
    otaur
    -0.64
    omorph
    -0.64
    POSITIVE LOGITS
     Jinping
    0.98
     appointed
    0.87
    oÄŁan
    0.85
     Hollande
    0.84
     Maduro
    0.81
     vowed
    0.81
     appoint
    0.77
    jri
    0.77
     Tayyip
    0.76
     Erdogan
    0.74
    Activations Density 0.311%

    No Known Activations