© 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. 26060
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "classes."

    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
    236
    +0.11
    0.7%
    174
    +0.10
    0.6%
    449
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    449
    +0.11
    0.01
    234
    +0.10
    0.01
    236
    +0.10
    0.01
    Negative Logits
    ·¸
    -3.46
    ĵ
    -3.35
    ¿½
    -3.25
    ĩ
    -3.19
    ľĵ
    -3.13
    Īĺ
    -3.09
    ¯
    -3.06
    Ħ
    -3.06
    Ł
    -3.04
    ²
    -3.03
    POSITIVE LOGITS
    heet
    2.37
    naire
    2.21
    heets
    2.13
    rooms
    1.92
    iors
    1.89
    liga
    1.76
     favor
    1.73
    sheet
    1.69
    papers
    1.69
    erialize
    1.68
    Activations Density 0.023%

    No Known Activations