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. 10-RES-JB
    6. 14667
    Prev
    Next
    INDEX
    Explanations

    locations with "Nor" in the name

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "Nor" or variations thereof, indicating location or context related to Northern regions or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eers
    -0.60
     Ic
    -0.59
     administrations
    -0.59
     thumbnail
    -0.57
     congress
    -0.57
     Merch
    -0.55
     Rampage
    -0.55
     dotted
    -0.55
     parentheses
    -0.54
     earnest
    -0.53
    POSITIVE LOGITS
    wegian
    1.42
    berto
    1.17
    wich
    1.16
    ris
    1.12
    folk
    1.10
    bert
    1.09
    walk
    1.05
    rish
    1.03
    vell
    1.02
    thodox
    0.94
    Activations Density 0.015%

    No Known Activations