© 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. 29919
    Prev
    Next
    INDEX
    Explanations

    instances of the "import" statement in programming code

    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
    467
    +0.13
    0.8%
    72
    +0.12
    0.7%
    174
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    174
    +0.13
    0.06
    72
    +0.12
    0.06
    204
    +0.11
    0.06
    Negative Logits
     devoted
    -1.99
     visited
    -1.73
    '?"
    -1.71
    --"
    -1.68
    ?'
    -1.55
     why
    -1.55
     decided
    -1.43
    idem
    -1.43
    dess
    -1.41
     indeed
    -1.38
    POSITIVE LOGITS
    ĻĤ
    1.81
    aggio
    1.81
    ¾
    1.72
    ¡
    1.68
    £
    1.64
    ®
    1.62
    ”.
    1.62
    urations
    1.62
     outlet
    1.58
    ior
    1.57
    Activations Density 0.252%

    No Known Activations