© 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. 26668
    Prev
    Next
    INDEX
    Explanations

    themes related to decay, deterioration, or decline

    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
    376
    +0.12
    0.7%
    2
    +0.11
    0.6%
    148
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    480
    +0.12
    0.01
    370
    +0.11
    0.01
    229
    +0.10
    0.01
    Negative Logits
     intervening
    -1.76
    '));
    -1.74
     distant
    -1.61
     entire
    -1.58
    '))
    -1.57
     same
    -1.56
     entirety
    -1.51
     successive
    -1.50
     happier
    -1.48
     whole
    -1.47
    POSITIVE LOGITS
    Ĵ
    2.88
    ģ
    2.81
    Ģ
    2.80
    Ł
    2.48
    ½
    2.40
    ±
    2.36
    ī
    2.34
    ª
    2.28
    ł
    2.26
    Ĭ
    2.26
    Activations Density 0.021%

    No Known Activations