© 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. 2-MLP-SM
    11. 25793
    Prev
    Next
    INDEX
    Explanations

    the word "deserving" or 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/2-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.2.hook_mlp_out
    Hook Layer
    2
    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
    +0.20
    1.1%
    265
    +0.16
    0.9%
    349
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    469
    +0.20
    0.02
    11
    +0.16
    0.02
    374
    +0.14
    0.01
    Negative Logits
    ---|
    -1.68
    omitempty
    -1.55
    agma
    -1.47
    ---|---|---
    -1.45
    yna
    -1.45
    PLIED
    -1.42
    elta
    -1.41
    legate
    -1.39
    ág
    -1.39
    amento
    -1.38
    POSITIVE LOGITS
    terday
    1.74
     roles
    1.50
     footsteps
    1.47
     first
    1.45
     course
    1.40
     his
    1.40
     firstly
    1.40
    kin
    1.38
     beginning
    1.36
     Day
    1.35
    Activations Density 0.250%

    No Known Activations