© 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. 25423
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate names or titles of concepts

    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
    98
    +0.14
    0.8%
    341
    +0.11
    0.6%
    233
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    341
    +0.14
    0.03
    91
    +0.11
    0.03
    60
    +0.11
    0.01
    Negative Logits
    arian
    -1.63
    asons
    -1.59
    icial
    -1.57
     favour
    -1.54
    inates
    -1.54
    arding
    -1.51
    onical
    -1.49
    inate
    -1.48
    arians
    -1.45
    ably
    -1.45
    POSITIVE LOGITS
    Ĥ¬
    1.58
    ↵Č
    1.50
    ĥ
    1.46
    ĻĤ
    1.43
    oly
    1.42
    ·¸
    1.41
    ¿
    1.40
    ÂĴ
    1.39
    ¶
    1.38
     ([**
    1.37
    Activations Density 0.244%

    No Known Activations