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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 3-RES-JB
    6. 8095
    Prev
    Next
    INDEX
    Explanations

    phrases related to environmental regulations and policies

    oai_token-act-pair · gpt-3.5-turbo

    references to "Clean" in various contexts, particularly related to environmental policies and regulations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    yip
    -0.86
    isSpecialOrderable
    -0.75
    doms
    -0.73
    eryl
    -0.72
    iage
    -0.71
     reper
    -0.68
    antically
    -0.68
    andom
    -0.67
    ussian
    -0.66
     deaf
    -0.65
    POSITIVE LOGITS
     Clean
    1.14
    Clean
    0.85
    ing
    0.82
    liness
    0.79
    clean
    0.77
     cleaner
    0.76
     Explicit
    0.75
    ergy
    0.74
    Techn
    0.73
     Space
    0.72
    Activations Density 0.006%

    No Known Activations