© 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. 28771
    Prev
    Next
    INDEX
    Explanations

    the repetition of the word "up" in various contexts

    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
    317
    +0.11
    0.6%
    297
    +0.10
    0.6%
    236
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    236
    +0.11
    0.04
    297
    +0.10
    0.03
    475
    +0.10
    0.04
    Negative Logits
    Ĺ
    -1.76
    ances
    -1.59
    ĥ½
    -1.57
    Ī
    -1.56
    antic
    -1.55
    ¿½
    -1.55
     such
    -1.54
    ©
    -1.53
    Ń
    -1.51
     plain
    -1.49
    POSITIVE LOGITS
    holder
    1.60
    fecture
    1.58
    hill
    1.54
    esan
    1.53
    vier
    1.50
    haus
    1.47
     trilogy
    1.43
    enstein
    1.40
    endar
    1.38
    holders
    1.37
    Activations Density 0.019%

    No Known Activations