© 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. 28091
    Prev
    Next
    INDEX
    Explanations

    references to specific locations or towns

    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
    156
    +0.16
    1.0%
    503
    +0.13
    0.8%
    182
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    31
    +0.16
    0.02
    503
    +0.13
    0.02
    182
    +0.12
    0.02
    Negative Logits
     '</
    -1.75
     risen
    -1.69
    EVER
    -1.63
     yours
    -1.62
     anything
    -1.57
     tear
    -1.55
     '')
    -1.55
     anyone
    -1.52
    opsies
    -1.46
    opsy
    -1.45
    POSITIVE LOGITS
    borg
    2.03
    vist
    1.91
    gary
    1.89
    ppo
    1.87
    för
    1.87
    ville
    1.80
    fors
    1.79
    aho
    1.78
    heim
    1.77
     Rapids
    1.75
    Activations Density 0.024%

    No Known Activations