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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. Residuals
    5. 1-RES-SM
    6. 26977
    Prev
    Next
    INDEX
    Explanations

    legal terms and court orders

    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
    365
    +0.14
    0.8%
    182
    +0.13
    0.7%
    111
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.14
    0.10
    271
    +0.13
    0.04
    156
    +0.13
    0.05
    Negative Logits
    cy
    -2.12
    pt
    -1.52
     lived
    -1.51
    power
    -1.41
     space
    -1.37
    apolis
    -1.37
    open
    -1.36
     everyday
    -1.36
     spaces
    -1.34
     appeared
    -1.33
    POSITIVE LOGITS
    EMENT
    2.11
    ONG
    1.78
    ERTY
    1.70
    INGS
    1.70
    ERR
    1.67
    imony
    1.66
    naire
    1.62
    erior
    1.62
    ICE
    1.62
    IVE
    1.61
    Activations Density 0.377%

    No Known Activations