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. 10-RES-JB
    6. 1861
    Prev
    Next
    INDEX
    Explanations

    economic and political terms and concepts, especially related to different ideologies and philosophies

    oai_token-act-pair · gpt-3.5-turbo

    terms and concepts related to economic theory and political philosophies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Veteran
    -0.80
     Flake
    -0.80
    osponsors
    -0.77
    ometown
    -0.76
     LOW
    -0.76
    yip
    -0.75
    oldown
    -0.73
    lease
    -0.72
    Kid
    -0.70
     Grenade
    -0.70
    POSITIVE LOGITS
     theory
    1.57
     theories
    1.55
     theorists
    1.52
     Theory
    1.35
     anthropology
    1.32
     philosophers
    1.31
     epist
    1.31
     hypotheses
    1.31
     sociology
    1.30
     rationality
    1.29
    Activations Density 0.316%

    No Known Activations