Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit 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. 9-RES-JB
    6. 500
    Prev
    Next
    INDEX
    Explanations

    negative myths and stereotypes about various subjects like gender, sexuality, and physical appearance

    oai_token-act-pair · gpt-3.5-turbo

    references to myths and stereotypes, particularly those that have negative effects on individuals or groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ptroller
    -0.84
    andestine
    -0.76
    shall
    -0.76
    etsk
    -0.74
    issions
    -0.72
    Delivery
    -0.72
    assador
    -0.70
    itness
    -0.70
    uddin
    -0.69
    otos
    -0.69
    POSITIVE LOGITS
     stereotypes
    1.24
     stereotype
    1.19
     stereotyp
    1.17
     notions
    1.09
     ingrained
    1.06
     biases
    1.03
     prejudice
    1.02
     prejudices
    0.99
     stigma
    0.98
     perpet
    0.95
    Activations Density 0.320%

    No Known Activations