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. 9-RES-JB
    6. 19048
    Prev
    Next
    INDEX
    Explanations

    information related to laws and regulations, particularly around medical and recreational drug use and legal bans

    oai_token-act-pair · gpt-3.5-turbo

    topics related to legal matters or legislation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    isine
    -0.78
    xual
    -0.76
     arte
    -0.73
    deen
    -0.72
    anu
    -0.72
    abilia
    -0.71
     psyche
    -0.70
    utenberg
    -0.68
     lyrics
    -0.68
     uncontroll
    -0.66
    POSITIVE LOGITS
     Connecticut
    1.01
    California
    0.98
     Maryland
    0.97
     California
    0.96
     Rhode
    0.96
    Alabama
    0.94
     Indiana
    0.94
    Arizona
    0.93
     Hawaii
    0.92
     Georgia
    0.92
    Activations Density 0.859%

    No Known Activations