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. 3-RES-JB
    6. 11040
    Prev
    Next
    INDEX
    Explanations

    references to racial dynamics and disparities, focusing on the context of white individuals

    oai_token-act-pair · gpt-3.5-turbo

    references to racial identity, specifically targeting the term "whites" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    QB
    -0.74
    yrinth
    -0.70
    ulous
    -0.68
    rolog
    -0.67
     WATCHED
    -0.66
    ctica
    -0.66
    abil
    -0.64
    raq
    -0.63
    HCR
    -0.63
    ESCO
    -0.63
    POSITIVE LOGITS
     whites
    1.02
     supremacists
    0.94
    paces
    0.88
    ervative
    0.88
    pace
    0.88
    folk
    0.86
     supremacist
    0.85
    lucent
    0.77
    \\\\\\\\
    0.77
    hirt
    0.76
    Activations Density 0.013%

    No Known Activations