© 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. 29372
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "ate" and related forms

    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
    +0.14
    0.8%
    144
    +0.13
    0.7%
    34
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    34
    +0.14
    0.03
    484
    +0.13
    0.03
    11
    +0.12
    0.03
    Negative Logits
     discriminated
    -1.85
    OVE
    -1.60
     smelled
    -1.58
    uster
    -1.54
     sing
    -1.51
    onen
    -1.48
    *](#
    -1.44
     say
    -1.43
    called
    -1.43
    OVA
    -1.42
    POSITIVE LOGITS
    ¬
    2.23
    ¿
    2.19
    ļ
    2.17
    Ļ
    1.95
    ¢
    1.94
    ®
    1.92
    °
    1.87
    ī
    1.85
    ł
    1.83
    ĩ
    1.82
    Activations Density 0.052%

    No Known Activations