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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 10-RES-JB
    11. 17260
    Prev
    Next
    INDEX
    Explanations

    phrases where there is a specific word or phrase marked by a unique character

    oai_token-act-pair · gpt-3.5-turbo

    scientific concepts and discussions related to medical and biological phenomena

    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
    minist
    -0.79
     wiser
    -0.75
    abouts
    -0.74
    ensibly
    -0.70
    ileaks
    -0.70
    atism
    -0.68
     imperson
    -0.67
     citiz
    -0.61
     disgruntled
    -0.61
     discipl
    -0.60
    POSITIVE LOGITS
    Researchers
    1.03
    Explore
    1.00
    Scientists
    0.93
    Abstract
    0.84
     Researchers
    0.84
    RESULTS
    0.80
    âĵĺ
    0.78
     Scientists
    0.78
    Professor
    0.77
    Phys
    0.76
    Activations Density 0.272%

    No Known Activations