© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 18366
    Prev
    Next
    INDEX
    Explanations

    mentions related to various regions and countries, specifically focusing on North African countries like Algeria and Morocco

    oai_token-act-pair · gpt-3.5-turbo

    references to Algeria and Moroccan connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    icle
    -0.80
    ramid
    -0.78
    odcast
    -0.78
    ku
    -0.75
    icles
    -0.74
    kus
    -0.74
    ODUCT
    -0.71
    creation
    -0.69
    rint
    -0.68
    BY
    -0.68
    POSITIVE LOGITS
     Alger
    1.03
     Algeria
    0.97
     cous
    0.84
     Morocco
    0.77
     Mubarak
    0.74
     Brah
    0.71
     Airlines
    0.69
     Hollande
    0.66
    ois
    0.66
     Tunis
    0.65
    Activations Density 0.008%

    No Known Activations