© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 7-RES-JB
    11. 24170
    Prev
    Next
    INDEX
    Explanations

    mentions of countries or territories

    oai_token-act-pair · gpt-3.5-turbo

    mentions of Uganda and its related geopolitical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    earable
    -0.87
    itbart
    -0.80
    alty
    -0.80
     accur
    -0.78
    cyclopedia
    -0.75
    idth
    -0.75
     bets
    -0.75
    creen
    -0.73
    aturdays
    -0.73
    ++++++++++++++++
    -0.69
    POSITIVE LOGITS
     Erit
    0.98
     Congo
    0.90
     Leone
    0.89
     Haram
    0.89
    andan
    0.85
     Cameroon
    0.85
     Niger
    0.85
     Sudan
    0.84
     Nigeria
    0.84
    ese
    0.83
    Activations Density 0.069%

    No Known Activations