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. 4-RES-JB
    6. 3176
    Prev
    Next
    INDEX
    Explanations

    medical and health-related terms and conditions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to health risks and physiological impacts

    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
    Secure
    -0.73
    trap
    -0.71
    Company
    -0.71
    Planet
    -0.71
     Armageddon
    -0.71
    iquette
    -0.69
    aws
    -0.69
    ç«
    -0.68
     Raymond
    -0.68
    drivers
    -0.68
    POSITIVE LOGITS
     susceptibility
    1.14
     endogenous
    1.05
     inhibit
    1.01
     uptake
    1.00
     dose
    0.99
     antioxidant
    0.99
     inflammation
    0.98
     oxidative
    0.98
     physiological
    0.97
     estrogen
    0.97
    Activations Density 0.174%

    No Known Activations