Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 5786
    Prev
    Next
    INDEX
    Explanations

    references to television shows, specifically "Mad Men" and "Real Housewives of [Location]."

    oai_token-act-pair · gpt-3.5-turbo

    references to popular television shows, particularly "Mad Men" and "Real Housewives."

    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
    hement
    -0.76
    staking
    -0.74
    uga
    -0.73
     dispersed
    -0.73
    ickr
    -0.70
     stren
    -0.70
    ntil
    -0.69
     grazing
    -0.67
    idav
    -0.66
     ende
    -0.66
    POSITIVE LOGITS
     Episode
    1.13
     airs
    1.01
    Episode
    0.99
     episode
    0.98
     Presents
    0.96
     Thrones
    0.96
     TV
    0.96
     Comedy
    0.95
     Channel
    0.95
    wives
    0.95
    Activations Density 0.113%

    No Known Activations