© 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
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. MLP Post
    5. 2-MLP-SM
    6. 27053
    Prev
    Next
    INDEX
    Explanations

    references to time durations, particularly focused on years and months

    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
    155
    +0.12
    0.7%
    185
    +0.11
    0.6%
    488
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    417
    +0.12
    0.05
    155
    +0.11
    0.04
    73
    +0.10
    0.03
    Negative Logits
    asons
    -1.69
    Äij
    -1.62
    llo
    -1.62
     Railroad
    -1.58
    afood
    -1.50
    cludes
    -1.49
     join
    -1.49
     Railway
    -1.48
    inta
    -1.44
     bikes
    -1.44
    POSITIVE LOGITS
    EGFR
    1.52
    esy
    1.44
    Argued
    1.44
     herself
    1.42
    TypeDef
    1.39
    ially
    1.38
    ECD
    1.36
    Ibid
    1.32
     \#
    1.32
    @"
    1.31
    Activations Density 0.240%

    No Known Activations