© 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. 1-RES-JB
    11. 15893
    Prev
    Next
    INDEX
    Explanations

    anti-Semitic terms and phrases

    oai_token-act-pair · gpt-3.5-turbo

    references to anti-Semitism and related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    avez
    -0.79
     NCT
    -0.77
    LEASE
    -0.69
    woods
    -0.67
    ITNESS
    -0.67
    amina
    -0.67
    Reviewer
    -0.67
     Wiggins
    -0.64
    foot
    -0.64
    work
    -0.64
    POSITIVE LOGITS
    Semitic
    1.00
    ophobic
    1.00
    ophobia
    0.97
    Semitism
    0.90
     slurs
    0.87
    ophe
    0.83
     tropes
    0.78
    geist
    0.74
     swast
    0.73
     prejudices
    0.72
    Activations Density 0.015%

    No Known Activations