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. 8-RES-JB
    6. 9521
    Prev
    Next
    INDEX
    Explanations

    phrases related to differences or variations

    oai_token-act-pair · gpt-3.5-turbo

    concepts and terms related to diversity and variation among individuals and groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    isman
    -0.67
    WARN
    -0.64
    mobi
    -0.64
     excess
    -0.62
    odon
    -0.62
     understatement
    -0.61
    iron
    -0.61
     omission
    -0.59
    Brave
    -0.58
    arton
    -0.58
    POSITIVE LOGITS
     depending
    1.20
     differing
    1.10
    paces
    1.06
     different
    1.02
     styles
    0.97
     varying
    0.96
     vying
    0.95
    styles
    0.90
     configurations
    0.89
     perspectives
    0.89
    Activations Density 0.292%

    No Known Activations