© 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. 1-RES-JB
    11. 16775
    Prev
    Next
    INDEX
    Explanations

    words related to physical bodily functions, particularly related to health and medical conditions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to electrolytes and their importance in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    innacle
    -0.68
    =-=-=-=-=-=-=-=-
    -0.66
    pez
    -0.65
    UNCH
    -0.64
     Sachs
    -0.60
     PAX
    -0.60
    awn
    -0.59
    ++++
    -0.58
    andra
    -0.57
     belief
    -0.57
    POSITIVE LOGITS
     Cumber
    1.17
    batch
    1.16
    itial
    0.94
    nces
    0.89
    stall
    0.88
    lio
    0.87
    berries
    0.87
    ricular
    0.86
    bies
    0.83
    TAIN
    0.82
    Activations Density 0.013%

    No Known Activations