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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 12224
    Prev
    Next
    INDEX
    Explanations

    phrases related to anti-Semitism

    oai_token-act-pair · gpt-3.5-turbo

    references to anti-Semitism

    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
     lift
    -0.70
     RO
    -0.65
     roll
    -0.65
     pack
    -0.64
     bark
    -0.64
     clearing
    -0.64
     exercise
    -0.63
     wr
    -0.63
     curve
    -0.62
     phys
    -0.61
    POSITIVE LOGITS
    Semitism
    3.75
    Semitic
    3.16
    Jewish
    2.07
    Jews
    1.66
    Sem
    1.47
    Israel
    1.41
     Jews
    1.38
     Jewish
    1.32
    Israeli
    1.28
     Judaism
    1.28
    Activations Density 0.017%

    No Known Activations