© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 0-RES-JB
    11. 23263
    Prev
    Next
    INDEX
    Explanations

    references to the Jewish community

    oai_token-act-pair · gpt-3.5-turbo

    references to the Jewish community

    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
     biome
    -0.76
     Ao
    -0.75
     hyd
    -0.70
     AU
    -0.68
     cone
    -0.66
     Bent
    -0.65
    âĶĢ
    -0.65
     Coral
    -0.65
    forcement
    -0.64
    burst
    -0.64
    POSITIVE LOGITS
     Jews
    3.83
    Jews
    3.40
    Jewish
    2.67
     Jewish
    2.64
     Jew
    2.46
     Judaism
    2.35
     Israelis
    2.22
     Palestinians
    2.02
     synagogue
    2.00
     Arabs
    2.00
    Activations Density 0.021%

    No Known Activations