© 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. 29329
    Prev
    Next
    INDEX
    Explanations

    the concept of existence or the state of being

    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
    44
    +0.14
    0.8%
    376
    +0.13
    0.8%
    65
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    44
    +0.14
    0.08
    65
    +0.13
    0.08
    356
    +0.13
    0.06
    Negative Logits
    Ĵ
    -2.54
    ¨
    -2.39
    ª
    -2.26
    ľ
    -2.22
    ©
    -2.21
    §
    -2.15
    ¦
    -2.14
    ķ
    -2.13
    ¥
    -2.09
    ŀ
    -2.08
    POSITIVE LOGITS
    ymmetric
    1.66
     unable
    1.64
     able
    1.62
     LIABLE
    1.60
    ijing
    1.54
    hdad
    1.53
    WARE
    1.48
    agland
    1.45
    wolf
    1.42
    zier
    1.40
    Activations Density 0.373%

    No Known Activations