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. 21217
    Prev
    Next
    INDEX
    Explanations

    phrases expressing the concept of wisdom

    oai_token-act-pair · gpt-3.5-turbo

    references to wisdom or knowledge in various contexts

    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
    ches
    -0.76
    ching
    -0.73
    chrom
    -0.69
    oos
    -0.69
    akedown
    -0.68
    ched
    -0.68
    Interstitial
    -0.67
    alien
    -0.65
    bing
    -0.65
    neys
    -0.64
    POSITIVE LOGITS
     wisdom
    1.10
    smanship
    0.89
    fulness
    0.84
     Advice
    0.80
     advice
    0.76
    avascript
    0.73
    cean
    0.73
     Wisdom
    0.71
    ility
    0.68
    acies
    0.68
    Activations Density 0.011%

    No Known Activations