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. 6-RES-JB
    6. 3155
    Prev
    Next
    INDEX
    Explanations

    proper names related to a person named Emanuel

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Emanuel."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    =-=-=-=-
    -0.78
    ailand
    -0.75
    reditary
    -0.75
    =-=-=-=-=-=-=-=-
    -0.74
    orders
    -0.74
    inness
    -0.72
    othal
    -0.72
    ruciating
    -0.72
    alien
    -0.72
    aredevil
    -0.70
    POSITIVE LOGITS
     Macron
    0.92
     Emanuel
    0.88
    eering
    0.77
    eer
    0.66
    stration
    0.64
    wald
    0.64
    eers
    0.60
     Emmanuel
    0.60
    manuel
    0.59
    Args
    0.59
    Activations Density 0.023%

    No Known Activations