© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 31060
    Prev
    Next
    INDEX
    Explanations

    expressions of desire or calls to action

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Neuron Alignment
    Index
    Value
    % of L₁
    156
    +0.18
    1.0%
    376
    +0.16
    0.9%
    85
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    85
    +0.18
    0.01
    231
    +0.16
    0.01
    277
    +0.13
    0.01
    Negative Logits
     BGCOLOR
    -1.71
    ARK
    -1.44
    SUM
    -1.44
    ){#
    -1.34
    nbsp
    -1.30
    izer
    -1.29
    ––––––––
    -1.28
    ASH
    -1.28
    CLUDE
    -1.27
    ization
    -1.26
    POSITIVE LOGITS
    ence
    1.53
    uis
    1.47
    bles
    1.45
     parties
    1.43
    ée
    1.41
    vu
    1.37
    ulous
    1.34
    '];
    1.33
    ées
    1.32
    cibly
    1.32
    Activations Density 0.028%

    No Known Activations