© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 22484
    Prev
    Next
    INDEX
    Explanations

    words related to the concept of "ability" or "capability."

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Neuron Alignment
    Index
    Value
    % of L₁
    12
    +0.12
    0.6%
    279
    +0.11
    0.6%
    23
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    279
    +0.12
    0.03
    291
    +0.11
    0.02
    410
    +0.10
    0.01
    Negative Logits
    ¸
    -2.62
    ·
    -2.36
    ¨
    -2.34
    ¢
    -2.27
    ¦
    -2.23
    ħ
    -2.20
    ª
    -2.17
    ²
    -2.06
    °
    -2.01
    ij
    -1.99
    POSITIVE LOGITS
     contradiction
    1.52
    ]>
    1.51
    LLOW
    1.51
    OOST
    1.51
    watson
    1.45
    $-
    1.42
    trl
    1.41
    olev
    1.41
    &+
    1.36
    mighty
    1.31
    Activations Density 0.398%

    No Known Activations