© 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. 1716
    Prev
    Next
    INDEX
    Explanations

    words related to the country of Macedonia

    oai_token-act-pair · gpt-3.5-turbo

    references to specific ethnic or national identities

    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
     Roundup
    -0.68
     Cumm
    -0.67
    tra
    -0.66
     cellul
    -0.66
     ACS
    -0.63
    recy
    -0.63
     Hodg
    -0.63
    rollers
    -0.63
     Row
    -0.62
    atts
    -0.62
    POSITIVE LOGITS
    onian
    3.44
    anian
    2.36
    nian
    2.36
    idian
    2.14
    ilian
    2.03
    inian
    1.90
    alian
    1.74
    IAN
    1.74
    ian
    1.71
    assian
    1.63
    Activations Density 0.021%

    No Known Activations