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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 0-RES-JB
    6. 723
    Prev
    Next
    INDEX
    Explanations

    phrases related to Iran or Iranian entities

    oai_token-act-pair · gpt-3.5-turbo

    mentions of Iran or Iranian-related topics

    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
    aun
    -0.77
    vier
    -0.71
    Clark
    -0.68
     Wilde
    -0.66
    jen
    -0.65
     hunts
    -0.65
    uden
    -0.65
    topia
    -0.64
     Clark
    -0.64
     pus
    -0.63
    POSITIVE LOGITS
     Iranian
    3.74
     Iranians
    2.95
    Iran
    2.85
     Tehran
    2.63
     Iran
    2.60
     Azerbai
    2.13
     Iraqi
    2.10
     Persian
    2.10
     Pakistani
    1.98
     Rouhani
    1.97
    Activations Density 0.019%

    No Known Activations