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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 7-RES-JB
    6. 7673
    Prev
    Next
    INDEX
    Explanations

    mention of countries

    oai_token-act-pair · gpt-3.5-turbo

    phrases that include the conjunction "and" followed by various nationalities or descriptors related to people

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     shelves
    -0.80
     horm
    -0.73
     payoff
    -0.72
     shel
    -0.72
     descriptor
    -0.71
    perty
    -0.70
     racks
    -0.70
     partitions
    -0.70
     tumors
    -0.69
    nosis
    -0.69
    POSITIVE LOGITS
    Italian
    0.96
     Croat
    0.96
    Indian
    0.92
     Anglo
    0.91
    gian
    0.91
    orean
    0.87
    German
    0.87
    English
    0.86
     Portuguese
    0.86
    Eastern
    0.85
    Activations Density 0.170%

    No Known Activations