© 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 EvalsExportsinterp-engineNEWAPI 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. 30221
    Prev
    Next
    INDEX
    Explanations

    references to celebrations or commemorative events

    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
    376
    +0.27
    1.6%
    156
    +0.25
    1.5%
    148
    +0.19
    1.1%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    46
    +0.27
    0.01
    148
    +0.25
    0.01
    367
    +0.19
    0.01
    Negative Logits
    IJ
    -1.65
    sdk
    -1.58
    nger
    -1.56
    §
    -1.55
    ħ
    -1.54
    âī¤
    -1.46
    OE
    -1.38
    ostat
    -1.35
    Supporting
    -1.34
    axon
    -1.34
    POSITIVE LOGITS
     techniques
    1.62
    tons
    1.51
     initial
    1.43
     duties
    1.41
     maneu
    1.40
     movements
    1.39
     characters
    1.37
     gestures
    1.37
     greet
    1.35
     ultr
    1.34
    Activations Density 0.070%

    No Known Activations