© 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. 24743
    Prev
    Next
    INDEX
    Explanations

    conjunctions, particularly the word "and."

    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
    5
    +0.13
    0.7%
    430
    +0.12
    0.7%
    476
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    5
    +0.13
    0.06
    430
    +0.12
    0.05
    461
    +0.11
    0.07
    Negative Logits
    ²
    -2.58
    ĸ´
    -2.41
    ¾
    -2.32
    ł
    -2.30
    ¼
    -2.27
    ·
    -2.25
    ľ
    -2.24
    Ĥ
    -2.22
    ij
    -2.22
    Ħ
    -2.21
    POSITIVE LOGITS
    icago
    1.66
    Table
    1.63
    ppat
    1.59
    OUTPUT
    1.57
    fiddle
    1.55
    biamo
    1.50
    visor
    1.49
    ++,
    1.47
     etc
    1.43
    ++)
    1.42
    Activations Density 0.516%

    No Known Activations