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. 0-RES-JB
    6. 23757
    Prev
    Next
    INDEX
    Explanations

    instances of the word "macro" appearing in the text

    oai_token-act-pair · gpt-3.5-turbo

    references to macroeconomic concepts or terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hern
    -0.76
     Susan
    -0.74
     Eleanor
    -0.74
     Trail
    -0.72
    requ
    -0.71
    leased
    -0.71
    boro
    -0.70
     Auth
    -0.69
    thal
    -0.68
    deen
    -0.67
    POSITIVE LOGITS
     macro
    4.05
     Macro
    3.15
     macros
    2.91
    mac
    1.61
     micro
    1.31
    Mac
    1.31
    Micro
    1.19
    micro
    1.13
     microscopic
    1.08
     Micro
    1.04
    Activations Density 0.009%

    No Known Activations