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. 10-RES-JB
    6. 3903
    Prev
    Next
    INDEX
    Explanations

    phrases related to skin reactions and medical conditions

    oai_token-act-pair · gpt-3.5-turbo

    references to health-related conditions and their effects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Mub
    -0.87
    bul
    -0.82
    Dou
    -0.81
    Bruce
    -0.80
     Symb
    -0.78
     Zig
    -0.77
     ANG
    -0.76
     marg
    -0.76
     Whitman
    -0.76
    zees
    -0.74
    POSITIVE LOGITS
    ire
    1.01
    orum
    0.95
    Ģ
    0.89
    io
    0.89
    ore
    0.85
    ORE
    0.85
    service
    0.83
    ort
    0.82
    services
    0.82
    iate
    0.82
    Activations Density 0.304%

    No Known Activations