Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. Residuals
    5. 1-RES-SM
    6. 26706
    Prev
    Next
    INDEX
    Explanations

    text related to the concept of maintenance in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ctigges/pythia-70m-deduped__res-sm_processed/1-res-sm
    Prompts (Dashboard)
    32,768 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    standard
    Context Size
    128
    Dataset
    EleutherAI/the_pile_deduplicated
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    156
    +0.16
    0.9%
    376
    +0.13
    0.8%
    365
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    141
    +0.16
    0.01
    304
    +0.13
    0.01
    41
    +0.10
    0.01
    Negative Logits
    ĨĴ
    -2.31
    ķ
    -2.30
    ½
    -2.23
    §
    -2.07
    Ĵ
    -2.06
    ¾
    -2.04
    Ī
    -1.84
    Ŀ
    -1.79
    Ľ
    -1.78
    ĸ´
    -1.75
    POSITIVE LOGITS
     routines
    1.74
     periods
    1.61
    Tracker
    1.61
     radius
    1.54
     tasks
    1.53
    station
    1.52
    emitter
    1.49
     interval
    1.48
     purposes
    1.48
    interval
    1.47
    Activations Density 0.084%

    No Known Activations