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. 16385
    Prev
    Next
    INDEX
    Explanations

    words related to social justice, activism, and policy change

    oai_token-act-pair · gpt-3.5-turbo

    key social issues and barriers that contribute to violence and discrimination

    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
    çͰ
    -0.71
    oln
    -0.69
     mathemat
    -0.67
    estial
    -0.66
    chart
    -0.65
    ITNESS
    -0.61
    furt
    -0.61
    okin
    -0.61
     Kash
    -0.61
    ISO
    -0.60
    POSITIVE LOGITS
     menace
    0.81
     Rhino
    0.73
     prejudice
    0.70
    terness
    0.69
    mong
    0.68
     Survivors
    0.68
    erno
    0.67
    worms
    0.66
    worm
    0.64
    rene
    0.64
    Activations Density 0.613%

    No Known Activations