© 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. 29128
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate high levels of loyalty or commitment

    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
    247
    +0.14
    0.8%
    380
    +0.13
    0.8%
    329
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    380
    +0.14
    0.01
    329
    +0.13
    0.01
    247
    +0.11
    0.01
    Negative Logits
     daÃŁ
    -1.48
     dB
    -1.47
     '</
    -1.47
     END
    -1.46
    anas
    -1.42
    ...](
    -1.41
     obese
    -1.40
    nt
    -1.40
    ++)
    -1.39
     else
    -1.39
    POSITIVE LOGITS
    iewicz
    2.10
    ovsky
    1.77
    icz
    1.73
    emente
    1.73
    Ł
    1.69
    °
    1.69
    zerba
    1.68
    iary
    1.67
     ov
    1.67
    ów
    1.65
    Activations Density 0.019%

    No Known Activations