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. 16744
    Prev
    Next
    INDEX
    Explanations

    terms related to ethnic and religious groups

    oai_token-act-pair · gpt-3.5-turbo

    references to ethnic or cultural groups and their historical contexts

    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
    ifice
    -0.80
     malf
    -0.76
    advertising
    -0.66
     optimization
    -0.66
    pletion
    -0.64
    performance
    -0.63
     rehab
    -0.62
    éĹ
    -0.62
     ellipt
    -0.62
     treadmill
    -0.62
    POSITIVE LOGITS
     Boko
    0.89
     Protestants
    0.88
     Presbyter
    0.87
     persecuted
    0.85
     Christians
    0.83
     revolt
    0.82
     Franc
    0.81
     revol
    0.80
     circumcised
    0.79
     oppressed
    0.79
    Activations Density 0.609%

    No Known Activations