© 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. 25243
    Prev
    Next
    INDEX
    Explanations

    terms related to mental health conditions, particularly depression and its associated impacts

    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
    76
    +0.14
    0.7%
    448
    +0.12
    0.6%
    190
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    76
    +0.14
    0.03
    448
    +0.12
    0.02
    416
    +0.11
    0.05
    Negative Logits
    ĸ´
    -3.27
    ·¸
    -3.14
    Ł
    -3.12
    Ľ
    -3.08
    ³
    -3.01
    ī
    -2.96
    ¶
    -2.94
    ·
    -2.88
    Ĥ¬
    -2.88
    ↵
    -2.85
    POSITIVE LOGITS
    hello
    1.69
    hall
    1.53
     entertained
    1.43
    eer
    1.39
    bund
    1.37
     reflected
    1.37
    fair
    1.36
    '),
    1.34
    thank
    1.32
    undry
    1.31
    Activations Density 1.864%

    No Known Activations