© 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. 14721
    Prev
    Next
    INDEX
    Explanations

    terms related to political figures and entities

    oai_token-act-pair · gpt-3.5-turbo

    references to significant political figures, locations, and historical contexts related to South Africa

    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
    ccording
    -0.76
    gyn
    -0.73
     overboard
    -0.70
    naissance
    -0.69
    yss
    -0.68
    raq
    -0.67
    tis
    -0.66
    lies
    -0.66
    nd
    -0.65
    earance
    -0.65
    POSITIVE LOGITS
     Gandhi
    0.92
     Mandela
    0.92
     ANC
    0.90
    sung
    0.89
     Zimbabwe
    0.81
    artz
    0.78
    atu
    0.74
     apartheid
    0.72
    wark
    0.72
    wana
    0.70
    Activations Density 0.094%

    No Known Activations