Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 5-RES-JB
    6. 12708
    Prev
    Next
    INDEX
    Explanations

    words related to social justice, equity, and discrimination, especially focusing on the experiences of marginalized communities

    oai_token-act-pair · gpt-3.5-turbo

    references to marginalized communities, particularly focusing on issues affecting Black and transgender individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    HL
    -0.79
    yss
    -0.75
    USS
    -0.71
    UMP
    -0.69
    staff
    -0.69
    LOCK
    -0.65
    inventoryQuantity
    -0.64
    åĬ
    -0.61
    uner
    -0.61
    PASS
    -0.61
    POSITIVE LOGITS
     who
    0.88
    folk
    0.79
    arettes
    0.76
    paces
    0.75
    hood
    0.73
     everywhere
    0.71
    ervatives
    0.70
     whom
    0.69
     marry
    0.69
    olics
    0.67
    Activations Density 0.104%

    No Known Activations