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. 16733
    Prev
    Next
    INDEX
    Explanations

    names or terms related to a specific person named Russo

    oai_token-act-pair · gpt-3.5-turbo

    references to specific names or characters, particularly "Rus" and "Rox."

    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
    opsy
    -0.67
    holders
    -0.67
     accessory
    -0.66
     removable
    -0.63
    ĺħ
    -0.62
     Sinclair
    -0.62
     hanging
    -0.60
     idol
    -0.60
    holder
    -0.59
     plaque
    -0.59
    POSITIVE LOGITS
     Rus
    1.33
    kies
    1.15
    byss
    1.12
    Rus
    1.07
    iets
    0.91
    coe
    0.89
    kie
    0.89
    ulkan
    0.89
    chem
    0.84
    ques
    0.82
    Activations Density 0.006%

    No Known Activations