© 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. 27037
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing the phrase "no matter."

    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
    163
    +0.12
    0.7%
    152
    +0.10
    0.6%
    479
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    163
    +0.12
    0.03
    223
    +0.10
    0.03
    399
    +0.10
    0.03
    Negative Logits
    .[]{
    -1.50
     blocker
    -1.44
    rieve
    -1.44
    arming
    -1.43
    avin
    -1.43
    smallcaps
    -1.43
    á»Ļ
    -1.42
    .’”
    -1.41
    rip
    -1.39
    Æ¡
    -1.39
    POSITIVE LOGITS
    ij
    3.53
    ķ
    3.36
    °
    3.26
    Ń
    3.22
    ħ
    3.21
    ·¸
    3.21
    ¥
    3.18
    İ
    3.16
    Ķ
    3.16
    ¿
    3.15
    Activations Density 0.269%

    No Known Activations