© 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. 1-RES-JB
    11. 10262
    Prev
    Next
    INDEX
    Explanations

    pharmaceutical-related terms or mentions in text

    oai_token-act-pair · gpt-3.5-turbo

    references to the pharmaceutical industry

    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
    Jenn
    -0.75
     Fork
    -0.74
    Bird
    -0.72
     Devil
    -0.71
    butt
    -0.70
    bird
    -0.68
     Devils
    -0.67
    ño
    -0.67
    nings
    -0.67
    WM
    -0.66
    POSITIVE LOGITS
    aceutical
    1.25
     pharmaceutical
    1.12
     Pharmaceutical
    0.95
     conflic
    0.92
     warr
    0.91
     therape
    0.89
    ategory
    0.87
     medications
    0.87
     chemist
    0.84
     drugs
    0.84
    Activations Density 0.010%

    No Known Activations