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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 21107
    Prev
    Next
    INDEX
    Explanations

    the name "Assad"

    oai_token-act-pair · gpt-3.5-turbo

    references to Bashar al-Assad and his political context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Magic
    -0.79
     SD
    -0.78
     Myst
    -0.71
     Alph
    -0.71
     Ink
    -0.71
     TM
    -0.69
     Dun
    -0.69
     Ta
    -0.68
     Lore
    -0.68
     AT
    -0.68
    POSITIVE LOGITS
    Assad
    3.39
    Syrian
    1.59
    Syria
    1.57
    Putin
    1.40
    Nusra
    1.29
    Islam
    1.22
    Sham
    1.22
    Saudi
    1.12
    Ukraine
    1.11
    NPR
    1.10
    Activations Density 0.014%

    No Known Activations