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. 8-RES-JB
    6. 4686
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to the Americas

    oai_token-act-pair · gpt-3.5-turbo

    words related to American identity or affiliations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fax
    -0.97
    sie
    -0.69
    igne
    -0.69
     Foods
    -0.66
    oping
    -0.62
    margin
    -0.62
    meat
    -0.61
    isers
    -0.61
    cember
    -0.61
    orders
    -0.60
    POSITIVE LOGITS
    icans
    1.01
    ican
    0.97
    ICAN
    0.95
    ushi
    0.87
    icas
    0.87
    gency
    0.85
    ilar
    0.80
    ility
    0.79
    tu
    0.79
    gdala
    0.77
    Activations Density 0.076%

    No Known Activations