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. 19662
    Prev
    Next
    INDEX
    Explanations

    References to business operations, contracts, and monopolies

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with economics and business structures

    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
     oneself
    -0.86
    enth
    -0.73
    ocene
    -0.71
    ometric
    -0.70
    otropic
    -0.64
    depending
    -0.62
    cair
    -0.62
    legged
    -0.62
    ugar
    -0.61
    )\
    -0.61
    POSITIVE LOGITS
     counterparts
    1.03
     counterpart
    0.93
     mates
    0.84
    mates
    0.80
     antics
    0.69
    cles
    0.69
     woes
    0.68
     rivals
    0.68
     brethren
    0.68
    ysis
    0.66
    Activations Density 0.592%

    No Known Activations