© 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. 23639
    Prev
    Next
    INDEX
    Explanations

    the word "assume" in various contexts

    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
    132
    +0.15
    0.9%
    278
    +0.12
    0.7%
    131
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    335
    +0.15
    0.05
    255
    +0.12
    0.05
    397
    +0.12
    0.05
    Negative Logits
     remar
    -1.41
    uities
    -1.40
     then
    -1.38
     nonzero
    -1.37
     deference
    -1.35
     Fis
    -1.34
     PTSD
    -1.34
    ity
    -1.33
     prejud
    -1.33
     conflicting
    -1.32
    POSITIVE LOGITS
    ĥ½
    1.93
    =”
    1.84
    etine
    1.68
    ICO
    1.68
    cheat
    1.64
    album
    1.64
    liner
    1.62
    BOX
    1.62
    ¼
    1.58
    iative
    1.55
    Activations Density 0.441%

    No Known Activations