Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 3-RES-JB
    6. 21552
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to various individuals and companies

    oai_token-act-pair · gpt-3.5-turbo

    words related to individuals or entities involved in legal or criminal contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ancest
    -0.81
    yip
    -0.74
     commissions
    -0.71
     smugglers
    -0.68
    soDeliveryDate
    -0.67
     quarters
    -0.65
    izoph
    -0.64
     hundred
    -0.62
     densely
    -0.62
    ongyang
    -0.61
    POSITIVE LOGITS
    uve
    0.85
    ãĥīãĥ©ãĤ´ãĥ³
    0.84
    atis
    0.73
    arde
    0.72
    uay
    0.71
    arie
    0.70
    EVA
    0.69
    hire
    0.68
    amines
    0.68
    ment
    0.67
    Activations Density 0.217%

    No Known Activations