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. 9-RES-JB
    6. 21257
    Prev
    Next
    INDEX
    Explanations

    locations or areas with specific characteristics such as labor shortages, high demand, low occurrence of illegal activity, high land prices, or specific environmental conditions

    oai_token-act-pair · gpt-3.5-turbo

    locations associated with specific conditions or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pload
    -0.86
    ãĤ´
    -0.79
    alion
    -0.73
    ingen
    -0.72
    ayson
    -0.69
    SON
    -0.68
    Released
    -0.68
    thing
    -0.67
     Doodle
    -0.67
    iasco
    -0.67
    POSITIVE LOGITS
     populations
    1.00
     population
    0.86
     populous
    0.84
     geographically
    0.82
     proximity
    0.81
     frequ
    0.80
     conducive
    0.79
     traditionally
    0.79
     frequent
    0.78
     rainfall
    0.78
    Activations Density 0.484%

    No Known Activations