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. 6-RES-JB
    6. 22189
    Prev
    Next
    INDEX
    Explanations

    phrases related to political campaigns and teams

    oai_token-act-pair · gpt-3.5-turbo

    references to political campaigns and their associated teams or organizations

    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
    Redd
    -0.85
     Hig
    -0.73
     Grade
    -0.71
     Oro
    -0.68
    DEP
    -0.67
    REG
    -0.66
     Fres
    -0.65
     Occ
    -0.63
     Ada
    -0.62
    essional
    -0.61
    POSITIVE LOGITS
    chair
    0.91
     disav
    0.82
     hires
    0.79
     playbook
    0.77
     chairman
    0.76
    hement
    0.75
     aides
    0.74
    ack
    0.73
     denies
    0.73
    acks
    0.72
    Activations Density 0.139%

    No Known Activations