© 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. 25911
    Prev
    Next
    INDEX
    Explanations

    references to "wire" and related terms in technical contexts

    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
    +0.16
    1.0%
    156
    +0.12
    0.7%
    256
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    229
    +0.16
    0.01
    256
    +0.12
    0.01
    161
    +0.12
    0.01
    Negative Logits
     respective
    -1.73
     certain
    -1.69
     different
    -1.68
     various
    -1.59
    TRODUCTION
    -1.55
     departing
    -1.51
     unwanted
    -1.50
     particular
    -1.50
     relaxing
    -1.47
    ancer
    -1.45
    POSITIVE LOGITS
    finder
    1.85
    yard
    1.82
    notes
    1.69
    tap
    1.64
    casts
    1.63
    frame
    1.62
    neck
    1.60
    itat
    1.58
    lei
    1.58
    grant
    1.57
    Activations Density 0.020%

    No Known Activations