© 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. 26129
    Prev
    Next
    INDEX
    Explanations

    the term "ACE" and possibly other references related to a specific category or designation

    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
    77
    +0.17
    1.0%
    219
    +0.11
    0.6%
    121
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    77
    +0.17
    0.02
    121
    +0.11
    0.01
    300
    +0.11
    0.01
    Negative Logits
    ¿½
    -3.21
    ı
    -2.92
    ²
    -2.88
    Ļª
    -2.86
    Ĺ
    -2.86
    Ĥ
    -2.84
    Į
    -2.84
    Īĺ
    -2.84
    ij
    -2.81
    Ħ
    -2.79
    POSITIVE LOGITS
    pool
    1.80
     Awards
    1.74
    venue
    1.55
     inhibitor
    1.51
    bellum
    1.50
    BUR
    1.50
    ENTIAL
    1.48
    maker
    1.48
    WORD
    1.47
    lane
    1.44
    Activations Density 0.070%

    No Known Activations