© 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. 29067
    Prev
    Next
    INDEX
    Explanations

    words associated with special offers or promotions

    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
    166
    +0.14
    0.9%
    286
    +0.11
    0.7%
    159
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    159
    +0.14
    0.01
    166
    +0.11
    0.01
    302
    +0.10
    0.01
    Negative Logits
    )){
    -1.64
    rian
    -1.64
     any
    -1.58
    ?'
    -1.56
    ching
    -1.56
    ta
    -1.55
    ?"
    -1.50
     bothered
    -1.48
     <
    -1.48
     rash
    -1.44
    POSITIVE LOGITS
    naire
    1.90
    lei
    1.85
    ista
    1.74
     Rptr
    1.74
    finder
    1.69
    ÃŃf
    1.67
    mith
    1.62
    kap
    1.56
    minist
    1.54
    nik
    1.52
    Activations Density 0.051%

    No Known Activations