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. 6-RES-JB
    6. 22922
    Prev
    Next
    INDEX
    Explanations

    examples of discrimination based on various personal characteristics, with a focus on sexual orientation

    oai_token-act-pair · gpt-3.5-turbo

    references to sexual orientation and related social justice issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    EMS
    -0.80
    ERG
    -0.75
     Oper
    -0.73
    cit
    -0.71
     Wast
    -0.71
    ICE
    -0.70
    IRC
    -0.68
    vae
    -0.67
     Prices
    -0.66
    umm
    -0.66
    POSITIVE LOGITS
     coloring
    0.87
     bias
    0.84
     discrimination
    0.82
     affiliation
    0.80
     ancestry
    0.80
     disorder
    0.78
     identity
    0.78
     Discrimination
    0.78
     orientation
    0.76
     preference
    0.74
    Activations Density 0.117%

    No Known Activations