© 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. 25017
    Prev
    Next
    INDEX
    Explanations

    references to concepts of truth and related therapeutic terms

    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
    461
    +0.14
    0.8%
    301
    +0.13
    0.7%
    269
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    461
    +0.14
    0.02
    25
    +0.13
    0.01
    341
    +0.12
    0.01
    Negative Logits
     death
    -1.77
     yours
    -1.69
     corpse
    -1.60
     crime
    -1.46
     gor
    -1.42
     did
    -1.39
     shooter
    -1.37
    gow
    -1.37
     grave
    -1.37
    eness
    -1.36
    POSITIVE LOGITS
    ulin
    1.74
    extend
    1.72
    unes
    1.59
    rangle
    1.55
    rian
    1.52
    dtd
    1.46
    replace
    1.46
    icip
    1.42
    anne
    1.41
    igue
    1.41
    Activations Density 0.169%

    No Known Activations