© 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. 31087
    Prev
    Next
    INDEX
    Explanations

    references to the SHA-256 cryptographic hash function

    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
    445
    +0.13
    0.7%
    391
    +0.12
    0.7%
    91
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    277
    +0.13
    0.02
    445
    +0.12
    0.02
    436
    +0.12
    0.02
    Negative Logits
    "?"
    -1.65
    rians
    -1.59
     hers
    -1.59
    rogens
    -1.55
    uppose
    -1.50
    rian
    -1.49
     her
    -1.49
     ?>
    -1.47
     indefinite
    -1.39
     eternity
    -1.39
    POSITIVE LOGITS
    esan
    1.65
    iliary
    1.57
    FC
    1.53
     pockets
    1.51
    nai
    1.49
    ģ
    1.48
    bsite
    1.47
    pile
    1.46
    igent
    1.45
    castle
    1.44
    Activations Density 0.056%

    No Known Activations