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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 2-RES-JB
    6. 54
    Prev
    Next
    INDEX
    Explanations

    terms related to extremist ideologies or movements, particularly the concept of "jihad."

    oai_token-act-pair · gpt-3.5-turbo

    terms related to jihad and jihadists

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    the word "jihad" and its variations

    oai_token-act-pair · gpt-4-turbo
    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
    ances
    -0.68
    ANC
    -0.67
     Vital
    -0.66
     Concord
    -0.65
     Celestial
    -0.64
     Gord
    -0.64
    Trust
    -0.64
    士
    -0.63
    clip
    -0.62
     Heavenly
    -0.62
    POSITIVE LOGITS
    zai
    1.01
     jihad
    0.95
    apons
    0.86
    istan
    0.86
     guiActiveUn
    0.82
    eers
    0.80
    hammad
    0.79
    ihad
    0.78
     jihadist
    0.77
     jihadists
    0.75
    Activations Density 0.006%

    No Known Activations