© 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. 11-RES-JB
    11. 2495
    Prev
    Next
    INDEX
    Explanations

    hyphenated terms related to healthcare policy and issues

    oai_token-act-pair · gpt-3.5-turbo

    references to healthcare issues and policies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     square
    -0.79
     Wonderland
    -0.68
     Cosby
    -0.65
     babies
    -0.65
     cc
    -0.64
    rawdownloadcloneembedreportprint
    -0.64
     Morrow
    -0.64
     rode
    -0.63
     flakes
    -0.63
     pencil
    -0.63
    POSITIVE LOGITS
    related
    1.77
    focused
    1.38
    management
    1.37
    safety
    1.33
    specific
    1.33
    oriented
    1.31
    protection
    1.31
    indust
    1.27
    sector
    1.26
    themed
    1.26
    Activations Density 0.066%

    No Known Activations