© 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. 25272
    Prev
    Next
    INDEX
    Explanations

    repetitions of a specific phrase or term

    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
    434
    +0.16
    1.0%
    52
    +0.15
    0.9%
    108
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    157
    +0.16
    0.05
    52
    +0.15
    0.05
    434
    +0.12
    0.05
    Negative Logits
    ¿½
    -2.16
    İ
    -2.08
    Ĥ
    -2.07
    Ĭ
    -2.05
    soever
    -1.99
    Ħ
    -1.76
    ĵ
    -1.75
    ´
    -1.75
    Ģ
    -1.73
    ©
    -1.70
    POSITIVE LOGITS
    cript
    2.13
    ktop
    1.90
    emente
    1.81
    borough
    1.78
    urance
    1.69
    heet
    1.69
    borg
    1.69
    cribe
    1.69
    ources
    1.66
    cribed
    1.60
    Activations Density 1.585%

    No Known Activations