© 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. 11-RES-JB
    11. 1829
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal terms and legislation

    oai_token-act-pair · gpt-3.5-turbo

    references to civil rights legislation and its implications on various groups, particularly regarding discrimination

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Canaver
    -0.90
    nikov
    -0.85
     Gaddafi
    -0.85
     Niet
    -0.83
     Carlo
    -0.80
     Roose
    -0.79
     Tomas
    -0.79
     Sturgeon
    -0.79
     Minion
    -0.78
    leaf
    -0.78
    POSITIVE LOGITS
     discrimination
    1.85
    discrimination
    1.75
     discriminatory
    1.69
     Discrimination
    1.63
     discriminate
    1.60
     discriminated
    1.53
     discriminating
    1.48
     discrim
    1.48
     accommodations
    1.39
     Equal
    1.38
    Activations Density 0.453%

    No Known Activations