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. 1-RES-JB
    6. 2906
    Prev
    Next
    INDEX
    Explanations

    mentions of specific terms or phrases related to business, such as monopolies, franchises, and specific company names

    oai_token-act-pair · gpt-3.5-turbo

    references to monopolies and similar competitive market structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    çͰ
    -0.76
     cylinders
    -0.74
    ance
    -0.69
    ļé
    -0.66
     exemptions
    -0.65
     gust
    -0.64
     highs
    -0.64
     blasts
    -0.64
     warrants
    -0.64
     emission
    -0.63
    POSITIVE LOGITS
    opoly
    0.92
    gamer
    0.90
     Warfare
    0.82
     Psychiat
    0.80
     Gamer
    0.79
    tsky
    0.79
    pson
    0.77
    berman
    0.77
    marine
    0.77
     Tactics
    0.75
    Activations Density 0.037%

    No Known Activations