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. 4-RES-JB
    6. 3759
    Prev
    Next
    INDEX
    Explanations

    words related to wisdom or being knowledgeable

    oai_token-act-pair · gpt-3.5-turbo

    references to wisdom and wise decision-making

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

    No Comments

    Negative Logits
    ĸļ
    -0.77
    alogue
    -0.74
    yip
    -0.72
    riages
    -0.72
    ette
    -0.70
    packages
    -0.70
     Gutenberg
    -0.68
    adr
    -0.66
    Haunted
    -0.66
    isite
    -0.64
    POSITIVE LOGITS
    guy
    0.95
     counsel
    0.82
     wise
    0.77
    ness
    0.76
    ass
    0.75
    lings
    0.74
     wisdom
    0.73
     advice
    0.73
     cred
    0.73
    eyed
    0.73
    Activations Density 0.013%

    No Known Activations