© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. MLP Post
    9. 2-MLP-SM
    11. 26832
    Prev
    Next
    INDEX
    Explanations

    temporal references related to time intervals or durations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ctigges/pythia-70m-deduped__mlp-sm_processed/2-mlp-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_mlp_out
    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
    23
    +0.12
    0.7%
    414
    +0.12
    0.7%
    497
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    410
    +0.12
    0.03
    414
    +0.12
    0.02
    73
    +0.11
    0.03
    Negative Logits
     Assistance
    -1.80
    izumab
    -1.76
     assistance
    -1.71
    ems
    -1.59
     aid
    -1.55
    %.
    -1.55
    vation
    -1.54
    rait
    -1.52
     would
    -1.51
    weight
    -1.50
    POSITIVE LOGITS
    iph
    1.44
     curl
    1.42
     threads
    1.40
     implication
    1.37
     laughter
    1.36
    ↵
    1.34
    ↵
    1.34
    ——
    1.31
     wrath
    1.31
     hop
    1.28
    Activations Density 0.121%

    No Known Activations