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. 17259
    Prev
    Next
    INDEX
    Explanations

    words related to balance, harmony, or equilibrium

    oai_token-act-pair · gpt-3.5-turbo

    references to balance and imbalances in various contexts

    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
     buried
    -0.70
     Nemesis
    -0.67
     eternity
    -0.65
     nano
    -0.63
     nickel
    -0.61
     recycle
    -0.61
     helic
    -0.60
     exposed
    -0.59
     die
    -0.59
     Dawkins
    -0.59
    POSITIVE LOGITS
    bal
    4.73
    Bal
    2.00
    balance
    1.91
    balanced
    1.76
     bal
    1.42
     Bal
    1.41
    bil
    1.22
     balancing
    1.18
    bol
    1.09
     BAL
    1.09
    Activations Density 0.011%

    No Known Activations