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. 20369
    Prev
    Next
    INDEX
    Explanations

    terms related to financial health and social welfare, particularly focusing on subsidies, taxes, and income levels of Americans

    oai_token-act-pair · gpt-3.5-turbo

    references to low-income populations and their needs

    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
    rontal
    -0.71
    Reloaded
    -0.69
    yss
    -0.67
    PDATE
    -0.66
    rawdownloadcloneembedreportprint
    -0.66
     awa
    -0.64
    WIND
    -0.62
    ASED
    -0.60
    cknowled
    -0.60
    ModLoader
    -0.59
    POSITIVE LOGITS
    hip
    0.89
    hips
    0.88
     alike
    0.83
    paces
    0.75
     who
    0.70
    riages
    0.68
    folk
    0.68
     (<
    0.67
    lings
    0.66
    ervatives
    0.65
    Activations Density 0.371%

    No Known Activations