© 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. 30920
    Prev
    Next
    INDEX
    Explanations

    mentions of options or configurations

    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
    314
    +0.16
    0.9%
    376
    +0.16
    0.9%
    300
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    300
    +0.16
    0.02
    314
    +0.16
    0.02
    66
    +0.14
    0.01
    Negative Logits
    ·¸
    -3.26
    Ļª
    -3.24
    »¿
    -2.94
    ĸ´
    -2.88
    ľĵ
    -2.86
    ľ
    -2.82
    Īĺ
    -2.76
    ĥ½
    -2.72
    ĥ
    -2.72
    ¿
    -2.70
    POSITIVE LOGITS
    imization
    2.22
    ophone
    1.83
    ariate
    1.70
    ista
    1.61
    olds
    1.60
    ème
    1.53
    ibase
    1.51
    imize
    1.50
    iÄĩ
    1.50
    ivat
    1.47
    Activations Density 0.055%

    No Known Activations