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. 0-RES-JB
    6. 22887
    Prev
    Next
    INDEX
    Explanations

    medical terms related to conditions and treatments

    oai_token-act-pair · gpt-3.5-turbo

    terms related to neonatal or death incidents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     chuck
    -0.69
     Meow
    -0.68
     House
    -0.67
     Tinker
    -0.64
     sponge
    -0.63
     Nob
    -0.63
     shaking
    -0.62
     recy
    -0.62
     mix
    -0.62
     spirits
    -0.62
    POSITIVE LOGITS
    atal
    4.72
    ativity
    1.22
    atum
    1.13
    adal
    1.11
    natal
    1.11
    unci
    1.06
    ates
    1.05
    aternal
    1.05
    atin
    1.04
    omic
    1.04
    Activations Density 0.011%

    No Known Activations