© 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. 8-RES-JB
    11. 8408
    Prev
    Next
    INDEX
    Explanations

    instances of the term "racist."

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "racist" and its variations in relation to discussions about race and racism

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    icular
    -0.82
    Delivery
    -0.77
    pad
    -0.76
    ITNESS
    -0.76
    earchers
    -0.74
    lishes
    -0.74
    arios
    -0.74
    tis
    -0.74
    CHA
    -0.69
    amina
    -0.69
    POSITIVE LOGITS
     slurs
    1.13
     prejudice
    0.91
     stereotyp
    0.90
     stereotypes
    0.87
     slur
    0.84
     stereotype
    0.84
     tendencies
    0.83
     tir
    0.80
     jokes
    0.80
     supremacist
    0.80
    Activations Density 0.037%

    No Known Activations