© 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. 25470
    Prev
    Next
    INDEX
    Explanations

    references to dates or time-related phrases in the text

    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
    496
    +0.11
    0.6%
    484
    +0.11
    0.6%
    369
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    423
    +0.11
    0.10
    499
    +0.11
    0.07
    397
    +0.10
    0.10
    Negative Logits
    oretical
    -1.86
     ')
    -1.55
    ishes
    -1.43
     shall
    -1.43
    ried
    -1.43
    nolimits
    -1.41
     genus
    -1.40
    most
    -1.39
    rying
    -1.38
    rious
    -1.38
    POSITIVE LOGITS
    ĻĤ
    6.08
    ¼
    4.82
    ®
    4.42
     ↵
    4.39
    4.39
    <|outofrange|>
    4.39
    č↵
    4.39
    ↵
    4.39
    4.39
    4.39
    Activations Density 1.291%

    No Known Activations