© 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. 2-RES-JB
    11. 9165
    Prev
    Next
    INDEX
    Explanations

    names related to the Arabic culture

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific individuals, particularly the name Malik

    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
    OME
    -0.74
    hire
    -0.73
    raged
    -0.70
    inction
    -0.68
    racted
    -0.65
    rep
    -0.64
    cess
    -0.63
    ĻĤ
    -0.62
    ocratic
    -0.62
    nard
    -0.61
    POSITIVE LOGITS
     Malik
    1.22
     Hasan
    1.21
    pedia
    0.86
    istan
    0.81
    imir
    0.80
     Ahmad
    0.79
    awi
    0.79
    ovic
    0.78
    zai
    0.77
    ova
    0.75
    Activations Density 0.011%

    No Known Activations