© 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. 26430
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate urgency or importance

    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%
    470
    +0.14
    0.8%
    264
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    470
    +0.24
    0.14
    70
    +0.14
    0.04
    390
    +0.12
    0.03
    Negative Logits
    ĸ
    -2.44
    ĵ
    -2.44
    ¥
    -2.40
    ¯
    -2.34
    §
    -2.34
    ķ
    -2.32
    ¿½
    -2.32
    Ĥ¬
    -2.32
    Ĺ
    -2.31
    ¢
    -2.28
    POSITIVE LOGITS
    .[]{
    1.80
    )](
    1.71
    []{
    1.67
     ðŁĻĤ
    1.58
    ).](
    1.58
     &
    1.54
    $.[]{
    1.50
    %),
    1.45
     together
    1.40
    )$-
    1.35
    Activations Density 2.584%

    No Known Activations