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. 4-RES-JB
    6. 5679
    Prev
    Next
    INDEX
    Explanations

    specific names or instances of the word "Mohamed"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Mohamed."

    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
    rost
    -0.82
    chnology
    -0.77
    nces
    -0.74
    naire
    -0.68
    naires
    -0.67
    ×Ļ×
    -0.66
    Scot
    -0.65
    Ñĭ
    -0.64
    age
    -0.64
    agall
    -0.63
    POSITIVE LOGITS
     Mohamed
    1.04
     Abdel
    0.82
     Mahmoud
    0.81
    indal
    0.81
     Sheikh
    0.80
     Ali
    0.80
    abad
    0.80
     Ibrahim
    0.79
     Hassan
    0.77
    ammad
    0.76
    Activations Density 0.005%

    No Known Activations