© 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 EvalsExportsAPI 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. 24950
    Prev
    Next
    INDEX
    Explanations

    terms related to invasive procedures or techniques

    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
    466
    +0.11
    0.6%
    413
    +0.11
    0.6%
    156
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    466
    +0.11
    0.12
    238
    +0.11
    0.03
    170
    +0.10
    0.05
    Negative Logits
     retired
    -1.52
     Formula
    -1.51
     Caption
    -1.46
     plaintiff
    -1.42
     Honorable
    -1.40
     painters
    -1.39
     applied
    -1.39
     painter
    -1.38
    ified
    -1.37
     referee
    -1.36
    POSITIVE LOGITS
    omb
    1.56
    thro
    1.50
    ellt
    1.48
    ten
    1.43
    ensa
    1.42
    ader
    1.37
    akk
    1.36
    itz
    1.35
    tid
    1.34
    én
    1.34
    Activations Density 2.804%

    No Known Activations