© 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. 29678
    Prev
    Next
    INDEX
    Explanations

    references to carpets or related flooring materials

    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
    404
    +0.11
    0.7%
    291
    +0.11
    0.7%
    376
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    291
    +0.11
    0.01
    404
    +0.11
    0.01
    319
    +0.11
    0.01
    Negative Logits
     particular
    -1.63
     supposed
    -1.57
     suppose
    -1.54
     mysterious
    -1.52
     precious
    -1.45
    >'
    -1.44
     rapid
    -1.43
     sudden
    -1.42
    ?'
    -1.41
     predetermined
    -1.36
    POSITIVE LOGITS
    bag
    2.19
    ström
    1.98
    ainen
    1.77
    vä
    1.70
    bank
    1.68
    ball
    1.67
    pile
    1.67
    boat
    1.65
    balls
    1.64
    notes
    1.60
    Activations Density 0.011%

    No Known Activations