© 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. 27682
    Prev
    Next
    INDEX
    Explanations

    instances of the word "innovative."

    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
    +0.41
    2.6%
    376
    +0.17
    1.1%
    246
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    156
    +0.41
    0.01
    246
    +0.17
    0.01
    51
    +0.13
    0.01
    Negative Logits
    enson
    -1.60
     shelf
    -1.54
    oto
    -1.51
    auer
    -1.48
    ene
    -1.42
    arden
    -1.39
    heimer
    -1.37
    .“
    -1.33
     Prize
    -1.32
    atche
    -1.30
    POSITIVE LOGITS
    ł
    2.51
    ¢
    2.47
    Īĺ
    2.21
    ķ
    2.20
    ¯
    2.12
    ļ
    2.07
    Ŀ
    2.04
    ŀ
    2.02
    ĸ
    2.02
    Ħ
    1.98
    Activations Density 0.019%

    No Known Activations