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. 8-RES-JB
    6. 16275
    Prev
    Next
    INDEX
    Explanations

    names, specifically the name "Michele Bachmann" in varying contexts

    oai_token-act-pair · gpt-3.5-turbo

    names related to Michele Bachmann and associated references

    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
     vomit
    -0.70
    ODUCT
    -0.66
     Tycoon
    -0.62
     Jericho
    -0.61
     derog
    -0.61
    ITY
    -0.58
     Sovere
    -0.58
    LEASE
    -0.57
    VICE
    -0.56
     Colossus
    -0.56
    POSITIVE LOGITS
    mann
    1.32
    ynski
    1.06
     Bach
    0.97
    pan
    0.93
    heit
    0.93
    ao
    0.92
    fried
    0.90
    illi
    0.86
    man
    0.86
    isan
    0.85
    Activations Density 0.043%

    No Known Activations