© 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. 29123
    Prev
    Next
    INDEX
    Explanations

    URLs related to technology-related online resources

    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
    349
    +0.14
    0.8%
    279
    +0.12
    0.7%
    466
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    349
    +0.14
    0.01
    279
    +0.12
    0.01
    421
    +0.11
    0.01
    Negative Logits
    Īĺ
    -4.95
    ·¸
    -4.93
    ĵ
    -4.90
    ĥ
    -4.78
    ĺ
    -4.59
    Ħ
    -4.59
    ¿½
    -4.57
    ´
    -4.55
    ħ
    -4.48
    ij
    -4.46
    POSITIVE LOGITS
    geries
    1.77
    antry
    1.71
    gery
    1.56
    lectual
    1.53
    aul
    1.49
    lop
    1.49
     Script
    1.46
    bian
    1.46
    coin
    1.45
    Script
    1.45
    Activations Density 0.009%

    No Known Activations