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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 3-RES-JB
    6. 1886
    Prev
    Next
    INDEX
    Explanations

    mentions related to the group "Muslim Brotherhood"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the Muslim Brotherhood and associations with them

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Glasgow
    -0.77
    acly
    -0.73
     Normandy
    -0.71
    aminer
    -0.68
    aceous
    -0.66
    ties
    -0.66
    pport
    -0.64
    kj
    -0.64
     EST
    -0.64
     Columbus
    -0.64
    POSITIVE LOGITS
     Brotherhood
    1.08
    hemy
    0.79
    ollah
    0.79
     informants
    0.76
     affili
    0.74
     dissidents
    0.73
     affiliates
    0.72
    guards
    0.71
     operatives
    0.71
     infiltr
    0.71
    Activations Density 0.009%

    No Known Activations