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. 1-RES-JB
    6. 18448
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to the name "Francis"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Francis."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    è¦ļéĨĴ
    -0.71
     owl
    -0.68
    rush
    -0.65
    ammy
    -0.62
     Abyssal
    -0.62
    Assembly
    -0.61
    umbai
    -0.61
    phis
    -0.60
    azeera
    -0.59
    iable
    -0.58
    POSITIVE LOGITS
     Francis
    1.29
    Franc
    1.09
    olini
    0.83
     Benedict
    0.81
     Xavier
    0.79
    olate
    0.74
     Bacon
    0.69
    Pope
    0.69
     Marcos
    0.68
     Pope
    0.67
    Activations Density 0.009%

    No Known Activations