© 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. 27022
    Prev
    Next
    INDEX
    Explanations

    references to movies, their titles, and discussions about various elements and themes within films

    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
    23
    +0.14
    0.8%
    318
    +0.13
    0.7%
    19
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    51
    +0.14
    0.06
    318
    +0.13
    0.01
    19
    +0.13
    0.05
    Negative Logits
    Ģ
    -2.27
    Ľ
    -2.24
    ¢
    -2.22
    ĨĴ
    -2.09
    ¾
    -2.08
    »¿
    -2.02
    »
    -2.01
    ĭ
    -1.99
    Ļª
    -1.94
    ¡
    -1.93
    POSITIVE LOGITS
    Decided
    1.70
    ':
    1.69
    :*
    1.55
    >'
    1.52
    iced
    1.52
    :**
    1.51
    '">
    1.49
    rceil
    1.48
    googleapis
    1.47
    '):
    1.46
    Activations Density 0.416%

    No Known Activations