© 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. 25684
    Prev
    Next
    INDEX
    Explanations

    terms related to independence or self-sufficiency

    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
    222
    +0.12
    0.6%
    175
    +0.12
    0.6%
    449
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    193
    +0.12
    0.02
    219
    +0.12
    0.02
    123
    +0.11
    0.01
    Negative Logits
     herself
    -1.82
    ples
    -1.78
    esis
    -1.70
    ian
    -1.63
     himself
    -1.59
    osphere
    -1.59
    dies
    -1.58
     quarters
    -1.55
     hosts
    -1.50
     itself
    -1.49
    POSITIVE LOGITS
    »
    2.40
    ŀ
    2.30
    ĸ
    2.20
    ¢
    2.15
    ↵
    2.09
    ↵↵
    2.09
    č↵
    2.09
    ↵
    2.09
    ↵
    2.09
    2.09
    Activations Density 0.373%

    No Known Activations