© 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. 28467
    Prev
    Next
    INDEX
    Explanations

    instances of severe negative outcomes or intense emotions related to health, behavior, or social situations

    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
    +0.23
    1.3%
    376
    +0.18
    1.0%
    274
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    444
    +0.23
    0.01
    274
    +0.18
    0.01
    477
    +0.12
    0.01
    Negative Logits
    Ī
    -2.38
    Ķ
    -2.36
    ĥ½
    -2.19
    Ĭ
    -2.17
    ħ
    -2.15
    §
    -2.11
    ĵ
    -2.08
    Ħ
    -2.05
    ĩ
    -2.05
    ķ
    -2.04
    POSITIVE LOGITS
     enough
    1.68
     INCIDENT
    1.54
    áĢ¬
    1.50
     Duty
    1.47
    {}{
    1.46
    band
    1.38
     âĻª
    1.37
     wage
    1.36
     ÂĹ
    1.33
     duties
    1.31
    Activations Density 0.012%

    No Known Activations