© 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. 26551
    Prev
    Next
    INDEX
    Explanations

    instances of the word "strange" and related descriptions

    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
    156
    +0.31
    1.8%
    376
    +0.18
    1.1%
    148
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    266
    +0.31
    0.02
    226
    +0.18
    0.01
    156
    +0.14
    0.01
    Negative Logits
    +.
    -1.62
    ories
    -1.47
    ene
    -1.45
    EEK
    -1.44
    ylene
    -1.42
    ULTS
    -1.39
    obo
    -1.39
    =====
    -1.38
     shelf
    -1.37
     Developer
    -1.35
    POSITIVE LOGITS
    Ł
    2.07
    ®
    1.85
    ĩ
    1.83
    wealth
    1.74
    ¿½
    1.66
    ł
    1.64
    Ļ
    1.58
     marriages
    1.58
    ¨
    1.57
    °
    1.52
    Activations Density 0.026%

    No Known Activations