© 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. 30937
    Prev
    Next
    INDEX
    Explanations

    the name "Chris" mentioned in various contexts

    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
    +0.17
    0.9%
    1
    +0.12
    0.7%
    474
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1
    +0.17
    0.05
    71
    +0.12
    0.04
    499
    +0.12
    0.04
    Negative Logits
    Ĭ
    -2.17
    ĥ½
    -2.17
    ·¸
    -2.14
    ¬
    -1.92
    ¿½
    -1.89
    ?”
    -1.80
    Īĺ
    -1.74
    ĭ
    -1.73
    ĺ
    -1.73
    Ĺ
    -1.64
    POSITIVE LOGITS
    abad
    1.75
    strand
    1.68
    àµį
    1.63
    ars
    1.58
    grade
    1.57
    esque
    1.57
    bery
    1.55
    bourne
    1.53
    corp
    1.52
    jax
    1.46
    Activations Density 0.084%

    No Known Activations