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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 10-RES-JB
    6. 16842
    Prev
    Next
    INDEX
    Explanations

    mentions related to the Islamic State (ISIS) in chat logs or news articles

    oai_token-act-pair · gpt-3.5-turbo

    references to the Islamic State (ISIS) and related geopolitical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     impeachment
    -0.72
     lev
    -0.69
     compos
    -0.69
     balcon
    -0.69
     discretionary
    -0.68
     appra
    -0.68
     intu
    -0.68
     depos
    -0.67
     pend
    -0.67
     electors
    -0.67
    POSITIVE LOGITS
     ISIL
    1.35
     ISIS
    1.31
     Daesh
    1.28
    Nusra
    1.24
    ISIS
    1.24
     Islamic
    1.15
    Islamic
    1.14
    iphate
    1.10
     Taliban
    1.02
     Iraq
    1.02
    Activations Density 0.098%

    No Known Activations