© 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. 0-MLP-SM
    11. 27151
    Prev
    Next
    INDEX
    Explanations

    instances of "saving" in various contexts

    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
    +0.13
    0.7%
    503
    +0.13
    0.7%
    239
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    503
    +0.13
    0.02
    239
    +0.13
    0.02
    194
    +0.12
    0.01
    Negative Logits
    else
    -1.87
    rent
    -1.75
    bling
    -1.70
     unfair
    -1.61
    untu
    -1.56
    ICO
    -1.53
    icing
    -1.51
    ru
    -1.51
    eles
    -1.46
    elles
    -1.46
    POSITIVE LOGITS
    ł
    2.31
    ĺ
    2.20
    ¢
    1.85
    į
    1.84
    ģ
    1.82
    ·
    1.81
    InstanceState
    1.80
    ¶
    1.79
    ¤
    1.78
    ŀ
    1.77
    Activations Density 0.328%

    No Known Activations