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. 4-RES-JB
    6. 23563
    Prev
    Next
    INDEX
    Explanations

    mentions of the Syrian leader Bashar al-Assad

    oai_token-act-pair · gpt-3.5-turbo

    references to Bashar al-Assad and related political contexts in Syria

    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
     Edinburgh
    -0.84
    OSP
    -0.75
    Recommend
    -0.72
    Scotland
    -0.71
     Pacers
    -0.69
    Wisconsin
    -0.68
    WARD
    -0.68
     Hawaiian
    -0.66
     Frozen
    -0.65
    owler
    -0.65
    POSITIVE LOGITS
     Haf
    1.13
     Assad
    1.11
     Bashar
    1.09
     Hussein
    0.96
    Assad
    0.95
     Tayyip
    0.86
    lers
    0.86
     Abbas
    0.86
    ascus
    0.85
    ibi
    0.79
    Activations Density 0.005%

    No Known Activations