Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 926
    Prev
    Next
    INDEX
    Explanations

    mentions of the country "Zimbabwe"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of Zimbabwe and its political context, particularly involving Robert Mugabe

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ++++++++++++++++
    -0.74
    naissance
    -0.74
    igm
    -0.74
    omore
    -0.73
    htaking
    -0.71
    antly
    -0.71
    Else
    -0.70
    innacle
    -0.67
    anguage
    -0.66
    ysis
    -0.64
    POSITIVE LOGITS
     Zimbabwe
    1.02
    imbabwe
    1.00
    istani
    0.74
    anu
    0.73
    uru
    0.70
    andan
    0.70
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    0.67
     Uzbek
    0.67
    eni
    0.66
     Leban
    0.66
    Activations Density 0.008%

    No Known Activations