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

    Neuronpedia

    Jacobian LensNEW
    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. 25239
    Prev
    Next
    INDEX
    Explanations

    phrases that express positivity and appreciation

    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
    264
    +0.13
    0.7%
    283
    +0.11
    0.6%
    6
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    440
    +0.13
    0.00
    291
    +0.11
    0.04
    6
    +0.11
    0.05
    Negative Logits
    verse
    -1.65
    amination
    -1.58
    *.
    -1.50
    示
    -1.43
    iliary
    -1.42
    teenth
    -1.38
     remaining
    -1.37
     enter
    -1.36
    ^](#
    -1.36
    er
    -1.36
    POSITIVE LOGITS
    Ļª
    2.35
    ↵↵
    2.06
    2.06
    ↵
    2.06
    2.06
            ↵
    2.06
    ↵↵
    2.06
    ↵↵
    2.06
    2.06
    2.06
    Activations Density 1.135%

    No Known Activations