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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 27732
    Prev
    Next
    INDEX
    Explanations

    instances of the word "promote" or its variations, indicating a focus on promotional activities or initiatives

    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
    +0.21
    1.2%
    376
    +0.21
    1.2%
    408
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    408
    +0.21
    0.02
    472
    +0.21
    0.02
    300
    +0.13
    0.02
    Negative Logits
    ardi
    -1.72
    ween
    -1.68
    ajan
    -1.61
    sel
    -1.57
    etc
    -1.52
    nio
    -1.48
    til
    -1.48
    shire
    -1.47
     recently
    -1.46
    enez
    -1.44
    POSITIVE LOGITS
    ĻĤ
    2.72
    ł
    2.70
    ĥ
    2.62
    ¼
    2.56
    Ĭ
    2.52
    Ĩ
    2.46
    Īĺ
    2.44
    ¤
    2.44
    ³
    2.36
    ¿
    2.32
    Activations Density 0.032%

    No Known Activations