© 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. 26601
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "merged" or related concepts of combining or consolidating entities

    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
    376
    +0.17
    1.0%
    162
    +0.10
    0.6%
    139
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    347
    +0.17
    0.01
    204
    +0.10
    0.01
    162
    +0.10
    0.01
    Negative Logits
    uns
    -1.57
    rian
    -1.46
     rewarded
    -1.44
    rians
    -1.38
    taient
    -1.37
    kte
    -1.36
     roses
    -1.35
     trained
    -1.35
    ographers
    -1.34
    ands
    -1.32
    POSITIVE LOGITS
    °
    1.66
    ów
    1.65
    opan
    1.65
    feit
    1.58
    idone
    1.57
     controls
    1.56
    £
    1.55
    ¸
    1.54
    »
    1.54
     area
    1.54
    Activations Density 0.006%

    No Known Activations