© 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. 26232
    Prev
    Next
    INDEX
    Explanations

    instances of the word "been"

    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
    287
    +0.13
    0.7%
    250
    +0.10
    0.6%
    470
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    44
    +0.13
    0.11
    42
    +0.10
    0.10
    304
    +0.10
    0.10
    Negative Logits
    ledge
    -1.48
    avel
    -1.47
    rop
    -1.43
    ror
    -1.41
    rophe
    -1.40
    bil
    -1.38
     unless
    -1.36
    rob
    -1.31
     fallen
    -1.27
     hate
    -1.25
    POSITIVE LOGITS
    ção
    1.57
    ÃŃ
    1.55
    ieron
    1.53
     Francisco
    1.44
     microenvironment
    1.41
    onical
    1.39
    zzi
    1.37
    icia
    1.37
    ctions
    1.35
    stances
    1.34
    Activations Density 0.106%

    No Known Activations