© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 28112
    Prev
    Next
    INDEX
    Explanations

    instances of the word "earliest" or related derivatives

    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
    +0.18
    1.0%
    156
    +0.16
    0.9%
    148
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    266
    +0.18
    0.01
    317
    +0.16
    0.01
    83
    +0.12
    0.01
    Negative Logits
    icin
    -1.74
    rier
    -1.67
     consequently
    -1.65
     accordingly
    -1.64
    derer
    -1.53
    ikh
    -1.50
    eper
    -1.47
    azure
    -1.46
    ue
    -1.46
     therefore
    -1.46
    POSITIVE LOGITS
     childhood
    1.72
     thoughts
    1.59
     realities
    1.57
    imates
    1.55
    tons
    1.53
     footsteps
    1.52
     wed
    1.47
     achievable
    1.47
     glimps
    1.46
     emergencies
    1.45
    Activations Density 0.014%

    No Known Activations