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. 17128
    Prev
    Next
    INDEX
    Explanations

    phrases related to different aspects of society and governance

    oai_token-act-pair · gpt-3.5-turbo

    references to concepts of power and social dynamics

    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
    ãĥīãĥ©
    -0.85
    emed
    -0.75
    Hours
    -0.74
    EMS
    -0.70
    usky
    -0.68
    Shop
    -0.66
     Powder
    -0.64
    rero
    -0.64
    pees
    -0.63
    rament
    -0.63
    POSITIVE LOGITS
     namely
    1.47
     whereby
    1.36
     whereas
    1.33
     wherein
    1.23
     insofar
    1.23
     thereby
    1.09
     hence
    1.09
     viz
    1.07
     ie
    1.06
     whence
    1.06
    Activations Density 0.317%

    No Known Activations