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. 6-RES-JB
    6. 5347
    Prev
    Next
    INDEX
    Explanations

    phrases related to the Islamic State (IS) or Daesh terrorist group

    oai_token-act-pair · gpt-3.5-turbo

    references to the Islamic State (IS) and related groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Hearth
    -0.74
     UCH
    -0.74
    eatures
    -0.72
    iture
    -0.72
     Seah
    -0.71
    osal
    -0.71
     PAX
    -0.71
    âĸ¬
    -0.70
     Volt
    -0.70
     Scotch
    -0.70
    POSITIVE LOGITS
     militants
    1.11
     insurgents
    0.94
     jihadists
    0.93
     caliphate
    0.91
     terrorists
    0.89
     insurgency
    0.89
     fighters
    0.88
     militant
    0.87
     jihad
    0.85
     extremists
    0.83
    Activations Density 0.032%

    No Known Activations