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. 18941
    Prev
    Next
    INDEX
    Explanations

    references to the Tea Party movement or Tea Party itself

    oai_token-act-pair · gpt-3.5-turbo

    references to the Tea Party movement and its political implications

    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
    ãĤ¨ãĥ«
    -0.92
    ĸļ
    -0.75
     STATS
    -0.74
     Siem
    -0.71
    weather
    -0.69
    above
    -0.68
    WAYS
    -0.68
     Gon
    -0.68
     Yi
    -0.67
    othy
    -0.66
    POSITIVE LOGITS
     Caucus
    1.04
     movement
    0.94
     darling
    0.93
     activists
    0.87
     ferv
    0.85
     caucus
    0.85
     activist
    0.85
     extremism
    0.85
     revolt
    0.84
     fanatic
    0.84
    Activations Density 0.039%

    No Known Activations