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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 25922
    Prev
    Next
    INDEX
    Explanations

    phrases related to time and dates

    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
    156
    +0.24
    1.4%
    271
    +0.14
    0.8%
    366
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    396
    +0.24
    0.19
    333
    +0.14
    0.16
    4
    +0.12
    0.18
    Negative Logits
     \*
    -1.62
     terminating
    -1.59
    inates
    -1.56
     spontaneously
    -1.53
    fered
    -1.50
    uscular
    -1.49
    inations
    -1.45
     divided
    -1.42
     dissoci
    -1.41
     subd
    -1.41
    POSITIVE LOGITS
    »¿
    2.66
    ±
    2.59
    ³
    2.52
    ĻĤ
    2.52
    ĨĴ
    2.49
    <|outofrange|>
    2.48
    2.48
    ↵
    2.48
    2.48
    <|outofrange|>
    2.48
    Activations Density 2.888%

    No Known Activations