© 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. 30493
    Prev
    Next
    INDEX
    Explanations

    numerical values indicating significant events or actions

    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
    354
    +0.11
    0.6%
    105
    +0.10
    0.6%
    473
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    438
    +0.11
    0.40
    53
    +0.10
    0.42
    56
    +0.10
    0.11
    Negative Logits
    ↵³³
    -1.66
    ermost
    -1.65
    áĢº
    -1.61
    entric
    -1.54
    veolar
    -1.53
    mog
    -1.51
    áĢ¯
    -1.47
    oka
    -1.47
    inction
    -1.46
     Hipp
    -1.45
    POSITIVE LOGITS
    ¸
    2.75
    «
    2.48
    ³
    2.28
    ¬
    2.27
    ĸ´
    2.22
    ¹
    2.18
    Ń
    2.12
    Ķ
    2.11
    »¿
    2.08
    µ
    2.01
    Activations Density 4.656%

    No Known Activations