© 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. 0-MLP-SM
    11. 27094
    Prev
    Next
    INDEX
    Explanations

    the occurrence of the word "up" in various contexts

    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/0-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.0.hook_mlp_out
    Hook Layer
    0
    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
    383
    +0.12
    0.7%
    36
    +0.10
    0.6%
    124
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    297
    +0.12
    0.09
    95
    +0.10
    0.09
    399
    +0.10
    0.09
    Negative Logits
    ¥
    -2.73
    Ĥ
    -2.60
    Ģ
    -2.55
    ł
    -2.54
    µ
    -2.48
    ¯
    -2.44
    ↵
    -2.37
    ↵
    -2.37
    č↵
    -2.37
    ↵
    -2.37
    POSITIVE LOGITS
    front
    1.35
    writers
    1.33
    craft
    1.33
     Koch
    1.29
    hog
    1.28
    hold
    1.28
    uchi
    1.27
    USP
    1.26
    jets
    1.25
    cale
    1.24
    Activations Density 0.129%

    No Known Activations