© 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. 30330
    Prev
    Next
    INDEX
    Explanations

    the term "ahu," which likely relates to a specific cultural or contextual reference

    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
    410
    +0.14
    0.8%
    49
    +0.12
    0.7%
    429
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    31
    +0.14
    0.01
    49
    +0.12
    0.01
    429
    +0.12
    0.01
    Negative Logits
     grade
    -1.82
    rceil
    -1.66
    uded
    -1.51
     latter
    -1.50
    TD
    -1.50
     semin
    -1.49
    )**
    -1.45
    MSC
    -1.43
    )/(
    -1.43
    )/((
    -1.43
    POSITIVE LOGITS
    ĻĤ
    2.30
    ļ
    1.73
    robe
    1.72
    º
    1.70
    hold
    1.67
    ½
    1.66
    ĸ
    1.60
    ¥
    1.56
    ī
    1.53
    obacterium
    1.52
    Activations Density 0.012%

    No Known Activations