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. 11-RES-JB
    6. 16223
    Prev
    Next
    INDEX
    Explanations

    mentions of the Islamist group Hamas and related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to the political situation and actions involving Hamas and related entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pokemon
    -0.96
     Bigfoot
    -0.92
    mson
    -0.89
    ÃĽ
    -0.89
    CV
    -0.88
    osaurus
    -0.86
    ratom
    -0.85
    Florida
    -0.84
     Tao
    -0.83
     Clemson
    -0.81
    POSITIVE LOGITS
     Hamas
    2.33
     Gaza
    2.12
    Gaza
    1.84
     Palestinian
    1.67
     Palestinians
    1.57
     IDF
    1.49
    Palestinian
    1.49
     rockets
    1.49
    Palest
    1.48
     Israelis
    1.45
    Activations Density 0.238%

    No Known Activations