© 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. 25411
    Prev
    Next
    INDEX
    Explanations

    references to cooking appliances and methods

    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
    +0.20
    1.2%
    78
    +0.12
    0.7%
    446
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    78
    +0.20
    0.01
    446
    +0.12
    0.01
    234
    +0.11
    0.01
    Negative Logits
    hes
    -1.85
    hem
    -1.80
    ?'
    -1.47
     foot
    -1.41
     bowel
    -1.34
    ```
    -1.33
    dle
    -1.31
     yours
    -1.29
    hemat
    -1.29
    ity
    -1.28
    POSITIVE LOGITS
    ÅĽci
    1.74
    "}](#
    1.68
    aceut
    1.66
    ģ
    1.65
    ī
    1.65
    ¸
    1.52
    vable
    1.51
    ulations
    1.49
    acia
    1.44
    BC
    1.44
    Activations Density 0.015%

    No Known Activations