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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 19840
    Prev
    Next
    INDEX
    Explanations

    words related to medical conditions and treatments with the prefix "oc"

    oai_token-act-pair · gpt-3.5-turbo

    words related to specific classes or categories

    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
     redundancy
    -0.74
    Reloaded
    -0.67
     lunch
    -0.67
     setbacks
    -0.62
     Hampshire
    -0.62
     Upton
    -0.62
     aside
    -0.62
     EntityItem
    -0.61
    shapeshifter
    -0.60
     fry
    -0.59
    POSITIVE LOGITS
    oc
    4.20
    OC
    1.99
    oco
    1.94
    oche
    1.94
    ocent
    1.91
    oca
    1.86
    ocl
    1.79
    ocon
    1.67
    ocr
    1.66
    ocy
    1.54
    Activations Density 0.010%

    No Known Activations