© 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. 4-RES-JB
    11. 14396
    Prev
    Next
    INDEX
    Explanations

    the word "discrimination"

    oai_token-act-pair · gpt-3.5-turbo

    words related to discrimination and inclusivity

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

    No Comments

    Negative Logits
     Siberian
    -0.70
     Despair
    -0.67
    BOOK
    -0.64
    ¥µ
    -0.64
    FORM
    -0.63
     Yug
    -0.63
     menstrual
    -0.61
    LOAD
    -0.60
     Sahara
    -0.59
    Downloadha
    -0.59
    POSITIVE LOGITS
    ount
    1.21
    onduct
    1.12
    ussion
    1.03
    uity
    1.00
    retion
    0.99
    acies
    0.99
    ornia
    0.96
    ussions
    0.94
    acia
    0.93
    ayne
    0.92
    Activations Density 0.010%

    No Known Activations