© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 3-RES-JB
    11. 16966
    Prev
    Next
    INDEX
    Explanations

    topics related to nuclear agreements or deals, particularly in the context of Iran

    oai_token-act-pair · gpt-3.5-turbo

    mentions of nuclear deals and agreements, specifically related to Iran

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Blizz
    -0.78
    alach
    -0.78
     Owens
    -0.78
     Oregon
    -0.73
    CAP
    -0.72
    hiro
    -0.72
    Columb
    -0.71
     Banner
    -0.71
    ãģĨ
    -0.70
     Cooke
    -0.69
    POSITIVE LOGITS
    ollah
    0.90
    enei
    0.89
     enrichment
    0.87
    hran
    0.79
     regime
    0.78
     Revolutionary
    0.72
     Sabha
    0.71
     blackmail
    0.71
     dissidents
    0.70
     Rouhani
    0.69
    Activations Density 0.019%

    No Known Activations