© 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. 2-MLP-SM
    11. 24006
    Prev
    Next
    INDEX
    Explanations

    elements related to numerical data and statistics

    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/2-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.2.hook_mlp_out
    Hook Layer
    2
    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
    159
    +0.13
    0.7%
    500
    +0.13
    0.7%
    194
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    420
    +0.13
    0.17
    376
    +0.13
    0.11
    159
    +0.12
    0.07
    Negative Logits
    ¦
    -1.65
    ¿
    -1.57
    ¯
    -1.45
    .**
    -1.40
    -1.38
    ®
    -1.36
    -1.34
    -1.34
    ____________
    -1.33
    ."_
    -1.33
    POSITIVE LOGITS
    ollo
    1.55
    orno
    1.47
    oton
    1.38
    oddsidemargin
    1.37
    ÑģÑĤво
    1.35
     quota
    1.33
    ierno
    1.32
    ialog
    1.32
     equals
    1.31
    ictionary
    1.31
    Activations Density 1.006%

    No Known Activations