© 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. 27696
    Prev
    Next
    INDEX
    Explanations

    instances of the word "gets."

    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
    376
    +0.17
    1.0%
    193
    +0.12
    0.7%
    53
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    378
    +0.17
    0.01
    146
    +0.12
    0.01
    66
    +0.12
    0.01
    Negative Logits
     myself
    -1.82
    bey
    -1.70
    ppler
    -1.58
     moonlight
    -1.45
     silence
    -1.43
    gg
    -1.42
    inen
    -1.38
     certain
    -1.34
    asma
    -1.34
     small
    -1.32
    POSITIVE LOGITS
    mith
    2.27
    istical
    1.98
    ystem
    1.79
    erving
    1.77
    eful
    1.75
    ince
    1.74
    minded
    1.72
    abad
    1.71
    hearted
    1.71
    cript
    1.71
    Activations Density 0.018%

    No Known Activations