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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 11636
    Prev
    Next
    INDEX
    Explanations

    numerical representations or counts

    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
    +0.11
    0.6%
    177
    +0.11
    0.6%
    11
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    51
    +0.11
    0.06
    325
    +0.11
    0.06
    351
    +0.11
    0.06
    Negative Logits
    erate
    -1.71
    bour
    -1.66
    ifications
    -1.51
    pires
    -1.50
    poons
    -1.49
    holders
    -1.46
    iner
    -1.46
    ine
    -1.43
    ingale
    -1.41
    ants
    -1.39
    POSITIVE LOGITS
    ¸
    1.88
    aho
    1.86
    ī
    1.82
    «
    1.74
    į
    1.64
    asion
    1.61
    0000000
    1.60
    st
    1.57
    âģĦ
    1.54
    RY
    1.54
    Activations Density 0.226%

    No Known Activations