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. 11-RES-JB
    6. 16883
    Prev
    Next
    INDEX
    Explanations

    terms related to the country Norway

    oai_token-act-pair · gpt-3.5-turbo

    references to Norway

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     IPM
    -0.61
    eers
    -0.60
     Tablet
    -0.57
     Merch
    -0.57
     uncomp
    -0.55
     jer
    -0.54
     Mandatory
    -0.53
     mate
    -0.52
     hots
    -0.52
     thumbnail
    -0.52
    POSITIVE LOGITS
    wegian
    1.56
    wich
    1.22
    berto
    1.16
    walk
    1.13
    bert
    1.09
    folk
    1.08
    fleet
    1.03
    quist
    1.00
    Cal
    0.98
    ris
    0.98
    Activations Density 0.025%

    No Known Activations