© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 4-RES-JB
    11. 387
    Prev
    Next
    INDEX
    Explanations

    words related to different sects within Islam, particularly Sunni and Shiite

    oai_token-act-pair · gpt-3.5-turbo

    mentions of Sunni and Shiite identities

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

    No Comments

    Negative Logits
    osal
    -0.99
    ATURE
    -0.88
     Myster
    -0.87
    ĸļ
    -0.84
    inventoryQuantity
    -0.77
    TYPE
    -0.77
     WATCHED
    -0.77
     Turing
    -0.76
    RIP
    -0.75
     Starship
    -0.72
    POSITIVE LOGITS
     supremacist
    0.88
     Arabs
    0.88
     Muslim
    0.87
     Islamist
    0.87
     Arab
    0.87
     insurgent
    0.85
     jihadists
    0.84
     nationalist
    0.84
     militant
    0.84
     sleeper
    0.83
    Activations Density 0.006%

    No Known Activations