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. 2-RES-SM
    6. 29491
    Prev
    Next
    INDEX
    Explanations

    notations or terms related to plasticity 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/2-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.2.hook_resid_post
    Hook Layer
    2
    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
    477
    +0.14
    0.8%
    502
    +0.12
    0.7%
    203
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    477
    +0.14
    0.04
    350
    +0.12
    0.03
    386
    +0.12
    0.01
    Negative Logits
    UAL
    -1.75
     wrath
    -1.70
     sexes
    -1.62
    GREEK
    -1.60
     LORD
    -1.59
    veis
    -1.55
    ald
    -1.54
    rian
    -1.52
     truths
    -1.50
    selves
    -1.49
    POSITIVE LOGITS
    acements
    1.71
    ĨĴ
    1.65
    aus
    1.60
    au
    1.58
    enum
    1.58
    iff
    1.54
    aced
    1.53
    anners
    1.53
    atinum
    1.53
    io
    1.52
    Activations Density 0.121%

    No Known Activations