© 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. 26841
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "Masters" and its variations

    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
    +0.14
    0.8%
    338
    +0.13
    0.8%
    389
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    338
    +0.14
    0.01
    344
    +0.13
    0.01
    1
    +0.11
    0.01
    Negative Logits
     gay
    -1.73
     transgender
    -1.64
     apolog
    -1.61
     lesbian
    -1.56
     pregnant
    -1.52
    rept
    -1.50
    derr
    -1.50
     miscar
    -1.50
    kte
    -1.48
     racist
    -1.48
    POSITIVE LOGITS
    boro
    2.01
    CPU
    1.61
    achusetts
    1.58
    CLK
    1.58
     Degree
    1.58
    bench
    1.57
    iewicz
    1.56
    helf
    1.51
    ôt
    1.51
    ikel
    1.50
    Activations Density 0.020%

    No Known Activations