© 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. 0-MLP-SM
    11. 28784
    Prev
    Next
    INDEX
    Explanations

    instances of the word "ini."

    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
    +0.15
    0.9%
    19
    +0.12
    0.7%
    410
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    134
    +0.15
    0.01
    19
    +0.12
    0.02
    465
    +0.10
    0.01
    Negative Logits
    ))$.
    -2.13
    ľĵ
    -1.98
    ))$,
    -1.92
    ĵ
    -1.84
    Īĺ
    -1.77
    )){
    -1.71
    ))$
    -1.71
    )\\
    -1.69
    riton
    -1.68
    %=
    -1.66
    POSITIVE LOGITS
    istical
    1.72
    ist
    1.72
    force
    1.62
    ematic
    1.61
    ett
    1.58
    etts
    1.57
    eno
    1.55
    ruptcy
    1.55
    âĢIJ
    1.54
    istically
    1.53
    Activations Density 0.019%

    No Known Activations