© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 28109
    Prev
    Next
    INDEX
    Explanations

    repetitive phrases indicating welcome or invitation

    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
    107
    +0.14
    0.8%
    14
    +0.13
    0.7%
    346
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    258
    +0.14
    0.35
    23
    +0.13
    0.33
    56
    +0.11
    0.09
    Negative Logits
    ¾
    -2.69
    ¿
    -2.69
    ·¸
    -2.67
    ²
    -2.59
    ľ
    -2.51
    ¯
    -2.45
    £
    -2.40
    ´
    -2.36
    Ļ
    -2.31
    ½
    -2.27
    POSITIVE LOGITS
    thur
    1.80
    borough
    1.73
    lights
    1.68
    elves
    1.62
    lain
    1.60
    croft
    1.52
     ghosts
    1.49
    pent
    1.49
    Bg
    1.48
    hum
    1.47
    Activations Density 3.874%

    No Known Activations