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. 6-RES-JB
    6. 5691
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Bashar" with varying activation strengths, likely indicating a focus on identifying references to a specific individual named Bashar in the context of Syria

    oai_token-act-pair · gpt-3.5-turbo

    mentions of Syrian President Bashar al-Assad

    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
    OSP
    -0.79
    Recommend
    -0.71
     Pacers
    -0.67
     cerv
    -0.66
    opsy
    -0.64
     LCS
    -0.62
     Edinburgh
    -0.61
     oats
    -0.61
    ursed
    -0.61
    YC
    -0.60
    POSITIVE LOGITS
     Haf
    1.13
     Hussein
    1.08
     Assad
    1.02
     Bashar
    0.94
     Tayyip
    0.94
    lers
    0.85
     Abbas
    0.84
    Assad
    0.82
     Za
    0.80
    terness
    0.78
    Activations Density 0.014%

    No Known Activations