© 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. 28525
    Prev
    Next
    INDEX
    Explanations

    phrases related to concepts of life and existence

    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
    310
    +0.16
    0.9%
    180
    +0.13
    0.7%
    111
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.16
    0.06
    406
    +0.13
    0.06
    26
    +0.10
    0.05
    Negative Logits
    ession
    -1.62
    essions
    -1.60
     prepared
    -1.56
     talks
    -1.53
     taught
    -1.52
     leverage
    -1.42
     gonna
    -1.38
     engagement
    -1.36
     theirs
    -1.33
    ages
    -1.33
    POSITIVE LOGITS
    §
    3.18
    Ļª
    3.01
    «
    2.74
    ¯
    2.72
    ĵ
    2.69
    ľ
    2.65
    ¥
    2.62
    »¿
    2.62
    ķ
    2.61
    ģ
    2.60
    Activations Density 0.035%

    No Known Activations