Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 4078
    Prev
    Next
    INDEX
    Explanations

    names of individuals named Mohammed

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Mohammed" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    chnology
    -0.69
    MpServer
    -0.66
    pick
    -0.66
    doors
    -0.65
    meal
    -0.65
    20439
    -0.63
    issue
    -0.60
    ALLY
    -0.59
    ttes
    -0.59
     CFR
    -0.59
    POSITIVE LOGITS
     Ali
    0.91
    anism
    0.91
    ammed
    0.88
    ammad
    0.86
    adesh
    0.80
    awa
    0.79
    hammad
    0.79
     ibn
    0.78
     Sheikh
    0.77
     Kush
    0.76
    Activations Density 0.015%

    No Known Activations