© 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. 26170
    Prev
    Next
    INDEX
    Explanations

    phrases that refer to the concept of obligation or responsibility

    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
    275
    +0.15
    0.8%
    12
    +0.13
    0.7%
    240
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    295
    +0.15
    0.26
    136
    +0.13
    0.23
    225
    +0.13
    0.23
    Negative Logits
    walk
    -1.63
     seated
    -1.59
     closer
    -1.40
    Connection
    -1.35
    agner
    -1.30
    stairs
    -1.28
     hovering
    -1.27
    park
    -1.27
     Clerk
    -1.27
    Dispatcher
    -1.26
    POSITIVE LOGITS
    hemat
    1.67
    iary
    1.64
     your
    1.63
    ibles
    1.58
     dollars
    1.54
    oretic
    1.53
    hesis
    1.42
    opot
    1.42
    Japanese
    1.42
    itations
    1.41
    Activations Density 1.539%

    No Known Activations