© 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. 0-RES-JB
    11. 10027
    Prev
    Next
    INDEX
    Explanations

    mentions of the country "Nigeria"

    oai_token-act-pair · gpt-3.5-turbo

    references to specific geographic locations

    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
     boot
    -0.69
    boot
    -0.66
     unloaded
    -0.66
     posts
    -0.65
     Polar
    -0.60
     polar
    -0.60
     diss
    -0.59
     intens
    -0.59
     Mass
    -0.59
     Twe
    -0.59
    POSITIVE LOGITS
    eria
    5.09
    erion
    1.54
    erie
    1.49
    eries
    1.34
    eri
    1.32
    ero
    1.32
    agate
    1.29
    era
    1.29
    ery
    1.24
    iera
    1.04
    Activations Density 0.006%

    No Known Activations