Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 5420
    Prev
    Next
    INDEX
    Explanations

    words related to respiratory conditions and remedies like coughing and ginger

    oai_token-act-pair · gpt-3.5-turbo

    terms related to coughing and respiratory illnesses

    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
     division
    -0.70
     divisions
    -0.70
     Values
    -0.69
    rb
    -0.66
     Modes
    -0.66
    isible
    -0.63
    waters
    -0.61
     Planetary
    -0.60
     Value
    -0.59
    tera
    -0.59
    POSITIVE LOGITS
     cough
    3.57
     coughing
    2.14
     ginger
    1.92
     Ginger
    1.31
     vomiting
    1.05
     Cumber
    0.99
     vomit
    0.93
     pony
    0.93
     chewing
    0.91
     headache
    0.89
    Activations Density 0.023%

    No Known Activations