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. 8260
    Prev
    Next
    INDEX
    Explanations

    mentions of specific public figures, particularly Richard Dawkins and Milo Yiannopoulos

    oai_token-act-pair · gpt-3.5-turbo

    mentions of prominent figures in atheism and controversial media personalities

    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
    illard
    -0.74
    ework
    -0.72
    ops
    -0.71
    ural
    -0.70
    awks
    -0.68
    OTS
    -0.68
    arist
    -0.68
    iliation
    -0.67
    ederation
    -0.67
    ive
    -0.65
    POSITIVE LOGITS
     Yiannopoulos
    0.91
     Jr
    0.74
    olini
    0.74
     Dawkins
    0.73
    Film
    0.73
    DragonMagazine
    0.72
     Coulter
    0.72
    quished
    0.72
    worms
    0.68
    onson
    0.68
    Activations Density 0.064%

    No Known Activations