© 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. 2-RES-JB
    11. 19722
    Prev
    Next
    INDEX
    Explanations

    mentions of the country Bangladesh

    oai_token-act-pair · gpt-3.5-turbo

    mentions of Bangladesh

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    edom
    -0.80
    vor
    -0.69
    etary
    -0.68
    orsche
    -0.68
     ellipt
    -0.67
     Eisenhower
    -0.67
     Reagan
    -0.66
    ttes
    -0.66
    LEASE
    -0.66
    byter
    -0.65
    POSITIVE LOGITS
     Bangladesh
    1.18
    istani
    1.09
     Bangl
    1.06
    istan
    1.02
    uran
    0.95
    adesh
    0.91
    abad
    0.90
    Bang
    0.90
    uru
    0.88
    halla
    0.84
    Activations Density 0.007%

    No Known Activations