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. 2-RES-JB
    6. 16974
    Prev
    Next
    INDEX
    Explanations

    terms related to legal matters and regulations

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "isc" and its variations, likely indicating a focus on discrimination or similar terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Despair
    -0.70
     Siberian
    -0.69
     Stard
    -0.67
    ¥µ
    -0.66
     Seymour
    -0.65
    worldly
    -0.63
    BOOK
    -0.63
     Yug
    -0.63
     Khe
    -0.62
    chest
    -0.60
    POSITIVE LOGITS
    onduct
    1.20
    ount
    1.10
    isc
    1.08
    urnal
    0.96
    uity
    0.90
    otal
    0.89
    retion
    0.89
    ayne
    0.86
    ussion
    0.85
    ot
    0.85
    Activations Density 0.008%

    No Known Activations