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. 21004
    Prev
    Next
    INDEX
    Explanations

    political contexts, such as mentions of elections, candidates, endorsements, and results

    oai_token-act-pair · gpt-3.5-turbo

    words related to competition and contest outcomes

    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
    wcs
    -0.79
     newsletters
    -0.75
    seys
    -0.74
     bedrooms
    -0.74
     spheres
    -0.72
    hops
    -0.72
    pec
    -0.69
    psc
    -0.69
    ense
    -0.69
    framework
    -0.68
    POSITIVE LOGITS
     fellow
    1.17
     Denis
    0.99
     Donald
    0.97
     Alexander
    0.96
     Sonny
    0.96
     Manuel
    0.95
     incumbent
    0.94
     Edwin
    0.91
     Leonardo
    0.91
     Valerie
    0.90
    Activations Density 0.237%

    No Known Activations