© 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. 4-RES-JB
    11. 7453
    Prev
    Next
    INDEX
    Explanations

    geographical locations, specifically focusing on the country Nigeria

    oai_token-act-pair · gpt-3.5-turbo

    mentions of Nigeria and related geographical contexts

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

    No Comments

    Negative Logits
    ++++++++++++++++
    -0.89
    ingham
    -0.73
    mble
    -0.71
     McDonnell
    -0.69
    ++++++++
    -0.69
    ablishment
    -0.68
    âĢ¢âĢ¢âĢ¢âĢ¢
    -0.67
    fare
    -0.67
     Syd
    -0.64
    âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ
    -0.64
    POSITIVE LOGITS
     Nigeria
    1.21
     Haram
    1.16
     Niger
    1.12
     Nigerian
    0.90
    vernment
    0.85
    iru
    0.81
     Cameroon
    0.81
    rahim
    0.80
     Boko
    0.79
    ongo
    0.79
    Activations Density 0.006%

    No Known Activations