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. 10-RES-JB
    6. 11893
    Prev
    Next
    INDEX
    Explanations

    mentions of the TV show "Mad Men"

    oai_token-act-pair · gpt-3.5-turbo

    references to the television series "Mad Men."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sight
    -0.75
    OPLE
    -0.73
    chnology
    -0.66
     caches
    -0.65
     stalls
    -0.61
     Vaugh
    -0.61
     accumulating
    -0.60
    ×Ļ×
    -0.59
     laps
    -0.59
     transitioning
    -0.56
    POSITIVE LOGITS
    eline
    1.18
    agascar
    1.14
    hya
    1.04
    oka
    0.99
    urai
    0.97
    rid
    0.97
    onna
    0.93
    ras
    0.91
    rig
    0.90
    house
    0.88
    Activations Density 0.014%

    No Known Activations