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. 6-RES-JB
    6. 6177
    Prev
    Next
    INDEX
    Explanations

    comparative adverbs indicating an increasing quantity or degree

    oai_token-act-pair · gpt-3.5-turbo

    the repeated use of the word "more" to indicate increasing quantities or prevalence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Theft
    -0.75
    gee
    -0.71
    ãĥĩ
    -0.70
     Reconstruction
    -0.70
    MAT
    -0.67
    comings
    -0.67
    folk
    -0.67
     Blow
    -0.66
    xtap
    -0.66
    assis
    -0.65
    POSITIVE LOGITS
     importantly
    0.88
     educated
    0.79
     stringent
    0.78
     advanced
    0.78
     sophisticated
    0.77
     technologically
    0.77
     intrusive
    0.75
     expensive
    0.74
     ambitious
    0.74
     invasive
    0.73
    Activations Density 0.036%

    No Known Activations