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. 8-RES-JB
    6. 15775
    Prev
    Next
    INDEX
    Explanations

    instances of medical conditions, practical problems, financial downturns, and issues related to conservative politics

    oai_token-act-pair · gpt-3.5-turbo

    topics related to health, disease, and societal impacts of behaviors and conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MpServer
    -0.70
    ilet
    -0.66
    itutes
    -0.65
    would
    -0.64
    achelor
    -0.64
    rophe
    -0.63
    Tomorrow
    -0.63
    without
    -0.63
    assies
    -0.62
    tops
    -0.62
    POSITIVE LOGITS
     misunderstanding
    1.03
     negligence
    0.91
    uitous
    0.90
     factors
    0.89
     inability
    0.87
     unwillingness
    0.86
     incompetence
    0.85
     inherent
    0.82
     ingenuity
    0.81
     neglect
    0.81
    Activations Density 0.606%

    No Known Activations