© 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. 26842
    Prev
    Next
    INDEX
    Explanations

    instances of the word "wreck" and its variations, indicating themes of destruction or damage

    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
    477
    +0.12
    0.7%
    456
    +0.12
    0.7%
    303
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    303
    +0.12
    0.01
    327
    +0.12
    0.01
    474
    +0.12
    0.01
    Negative Logits
    '));
    -1.61
    '))
    -1.61
     hereby
    -1.58
    rogens
    -1.52
    uka
    -1.51
     descent
    -1.47
    "))
    -1.47
    '">
    -1.45
    Developer
    -1.45
    Generated
    -1.40
    POSITIVE LOGITS
    ±
    2.36
    ®
    2.21
    Ģ
    2.20
    °
    2.19
    ´
    2.16
    ©
    2.15
    ¤
    2.05
    Ł
    2.02
    İ
    2.00
    ¸
    1.96
    Activations Density 0.013%

    No Known Activations