© 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. 26937
    Prev
    Next
    INDEX
    Explanations

    descriptive adjectives conveying positive or negative evaluations

    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
    310
    +0.14
    0.7%
    327
    +0.12
    0.7%
    454
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    327
    +0.14
    0.12
    496
    +0.12
    0.06
    310
    +0.11
    0.06
    Negative Logits
    ¯
    -2.79
    ¨
    -2.73
    IJ
    -2.63
    ¬
    -2.51
    ²
    -2.51
    ±
    -2.50
    ¤
    -2.47
    ¶
    -2.46
    £
    -2.44
    ¼
    -2.43
    POSITIVE LOGITS
    ()</
    1.62
    ulate
    1.41
    .$
    1.36
    amente
    1.35
    dated
    1.32
     mamm
    1.31
    ViewById
    1.30
    ear
    1.30
    iod
    1.29
    plus
    1.29
    Activations Density 3.071%

    No Known Activations