© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 2-RES-JB
    11. 17428
    Prev
    Next
    INDEX
    Explanations

    words related to health conditions and medical procedures, such as conditions like cystic fibrosis and terms like "catalysts."

    oai_token-act-pair · gpt-3.5-turbo

    words related to various types of scientific analyses or studies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ancestral
    -0.70
    fecture
    -0.68
     skelet
    -0.64
     seasoning
    -0.63
    shoot
    -0.60
    BUG
    -0.59
     multim
    -0.59
     obligated
    -0.58
     safegu
    -0.58
     culturally
    -0.58
    POSITIVE LOGITS
    sts
    1.22
    uffs
    0.98
    ock
    0.79
    ocks
    0.77
    mart
    0.77
    cape
    0.77
    rencies
    0.76
    rand
    0.76
    ubs
    0.76
    arget
    0.75
    Activations Density 0.012%

    No Known Activations