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. 20727
    Prev
    Next
    INDEX
    Explanations

    people's names, specifically the name "Andrea"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of a specific individual named Andrea

    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
    lasses
    -0.96
    Ħ¢
    -0.88
    mares
    -0.88
    lining
    -0.86
    ghai
    -0.84
    emouth
    -0.83
    onew
    -0.81
    azer
    -0.80
    INESS
    -0.80
    osuke
    -0.79
    POSITIVE LOGITS
     Rossi
    1.07
     Tant
    0.77
     Ces
    0.77
     Grimes
    0.76
    ption
    0.74
     Devi
    0.74
    ptions
    0.73
    zzo
    0.72
     Michele
    0.67
     Netanyahu
    0.66
    Activations Density 0.074%

    No Known Activations