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. 26715
    Prev
    Next
    INDEX
    Explanations

    words related to types of software or digital applications

    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
    +0.13
    0.7%
    297
    +0.11
    0.7%
    246
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    297
    +0.13
    0.02
    246
    +0.11
    0.02
    351
    +0.11
    0.02
    Negative Logits
     vain
    -2.05
    ©
    -1.82
     lonely
    -1.71
     nowhere
    -1.65
     satisfied
    -1.61
     unhappy
    -1.61
    ĺ
    -1.61
    Į
    -1.60
    ++){
    -1.58
     happier
    -1.58
    POSITIVE LOGITS
    ificial
    2.08
    amento
    2.01
    house
    1.99
    nement
    1.98
    ports
    1.89
    makers
    1.83
    guide
    1.80
    aceut
    1.80
    markets
    1.79
    houses
    1.78
    Activations Density 0.143%

    No Known Activations