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. 4-RES-JB
    6. 7932
    Prev
    Next
    INDEX
    Explanations

    medical terms related to drugs, diseases, and conditions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to medical conditions and treatments

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

    No Comments

    Negative Logits
    earchers
    -0.95
    cedented
    -0.95
    ĸļ
    -0.86
    DragonMagazine
    -0.85
     Twain
    -0.85
    krit
    -0.83
    stretched
    -0.80
    soDeliveryDate
    -0.79
    piece
    -0.79
    HCR
    -0.78
    POSITIVE LOGITS
     activity
    0.97
     substances
    0.95
     tendencies
    0.93
     diseases
    0.92
     behaviour
    0.92
     factors
    0.91
     behavior
    0.89
     lifestyles
    0.88
     organisms
    0.86
     properties
    0.86
    Activations Density 0.070%

    No Known Activations