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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 4674
    Prev
    Next
    INDEX
    Explanations

    references to a specific geographical location, specifically, Palestine

    oai_token-act-pair · gpt-3.5-turbo

    references to Palestine and related geopolitical 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
    Dragon
    -0.78
    dragon
    -0.74
     dragon
    -0.69
     DRAGON
    -0.68
     coils
    -0.67
     dracon
    -0.67
     reflex
    -0.66
     ang
    -0.66
     gust
    -0.65
     lure
    -0.64
    POSITIVE LOGITS
     Palestine
    3.78
    Palestinian
    2.02
     Zionism
    2.00
     Jerusalem
    1.91
     Palestinian
    1.87
     Palestinians
    1.82
    Palest
    1.78
     Gaza
    1.78
    Gaza
    1.78
     Palestin
    1.72
    Activations Density 0.017%

    No Known Activations