© 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. 26364
    Prev
    Next
    INDEX
    Explanations

    expressions related to feelings of inferiority

    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
    +0.19
    1.1%
    317
    +0.14
    0.8%
    487
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    317
    +0.19
    0.01
    370
    +0.14
    0.01
    487
    +0.11
    0.01
    Negative Logits
    ĨĴ
    -2.72
    Ħ
    -2.64
    ³
    -2.58
    Ī
    -2.51
    ĥ½
    -2.43
    Ĵ
    -2.41
    «
    -2.41
    Ĥ
    -2.34
    »
    -2.30
    Ń
    -2.27
    POSITIVE LOGITS
    ize
    1.75
     positions
    1.72
     speakers
    1.68
    ized
    1.62
    inib
    1.56
    ately
    1.55
    imize
    1.47
    Hung
    1.46
    imately
    1.45
     speaking
    1.43
    Activations Density 0.013%

    No Known Activations