© 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. 24757
    Prev
    Next
    INDEX
    Explanations

    references to support or endorsement

    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
    207
    +0.13
    0.7%
    92
    +0.12
    0.6%
    386
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    361
    +0.13
    0.04
    104
    +0.12
    0.03
    431
    +0.11
    0.03
    Negative Logits
    Ļª
    -2.04
    Ī
    -1.97
    Ł
    -1.74
    '."
    -1.62
    ĻĤ
    -1.56
    »¿
    -1.54
    ()).
    -1.54
    ħ
    -1.52
     behalf
    -1.49
     intent
    -1.49
    POSITIVE LOGITS
    ricane
    1.48
    dog
    1.44
    verse
    1.38
    cumin
    1.36
    ollar
    1.30
    ween
    1.29
    isman
    1.29
    gauge
    1.28
    teenth
    1.28
    IDTH
    1.26
    Activations Density 0.553%

    No Known Activations