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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 12073
    Prev
    Next
    INDEX
    Explanations

    mentions of the retail chain Walmart and its variations in context

    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
    369
    +0.23
    1.3%
    174
    +0.15
    0.9%
    144
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    174
    +0.23
    0.03
    369
    +0.15
    0.01
    410
    +0.11
    0.03
    Negative Logits
    Ļª
    -2.03
    üssen
    -1.56
    helial
    -1.55
    attery
    -1.54
    ĨĴ
    -1.53
    jest
    -1.52
    öm
    -1.51
    ocard
    -1.41
    asmod
    -1.40
    onal
    -1.40
    POSITIVE LOGITS
    die
    1.58
    ientes
    1.58
    TON
    1.51
    warz
    1.51
     dimensional
    1.50
    holder
    1.49
     zone
    1.44
    doms
    1.44
    iers
    1.41
    nuts
    1.40
    Activations Density 0.271%

    No Known Activations