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. 26807
    Prev
    Next
    INDEX
    Explanations

    actions related to sending and forwarding messages

    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
    376
    +0.21
    1.2%
    53
    +0.15
    0.8%
    156
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    259
    +0.21
    0.03
    63
    +0.15
    0.03
    490
    +0.14
    0.02
    Negative Logits
    hood
    -1.50
    OST
    -1.48
    isms
    -1.47
    Inflater
    -1.41
    »
    -1.39
    assic
    -1.37
    ½
    -1.36
    ismo
    -1.35
    ism
    -1.33
    uity
    -1.30
    POSITIVE LOGITS
    imental
    2.62
    inel
    2.14
     notifications
    1.83
    mail
    1.82
    gado
    1.75
     notification
    1.68
     plain
    1.62
    ked
    1.59
     false
    1.56
    ledge
    1.55
    Activations Density 0.109%

    No Known Activations