Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 8840
    Prev
    Next
    INDEX
    Explanations

    mentions of private insurance or private sectors in the context of coverage, incentives, investments, and proposals

    oai_token-act-pair · gpt-3.5-turbo

    references to private sector involvement and entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    xual
    -0.97
    è¦ļéĨĴ
    -0.76
    older
    -0.71
    icago
    -0.70
    ologies
    -0.70
     Scroll
    -0.69
    orsi
    -0.68
    obo
    -0.67
    DAY
    -0.67
     Cabrera
    -0.67
    POSITIVE LOGITS
     sector
    1.18
     equity
    0.97
    sector
    0.97
     Sector
    0.86
     sectors
    0.83
     affairs
    0.83
     entities
    0.82
     ownership
    0.81
     partnerships
    0.81
     contractors
    0.79
    Activations Density 0.019%

    No Known Activations