© 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. 0-RES-JB
    11. 8250
    Prev
    Next
    INDEX
    Explanations

    mentions of the country Bolivia and related proper nouns

    oai_token-act-pair · gpt-3.5-turbo

    repetitions of the name "Bol," particularly in a political context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sock
    -0.70
     withholding
    -0.68
    Race
    -0.67
    ÙIJ
    -0.64
     withheld
    -0.63
    gamer
    -0.63
    STON
    -0.61
     hist
    -0.61
     synagogue
    -0.61
    HM
    -0.60
    POSITIVE LOGITS
     Bol
    4.11
     bol
    2.15
     Bolivia
    1.83
    bol
    1.82
     Bolt
    1.54
     Colomb
    1.32
     Venezuelan
    1.26
     Venezuel
    1.25
     Maduro
    1.17
     Bolton
    1.17
    Activations Density 0.017%

    No Known Activations