© 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. 25434
    Prev
    Next
    INDEX
    Explanations

    emotionally positive experiences or sentiments expressed in the text

    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
    323
    +0.13
    0.7%
    82
    +0.12
    0.7%
    424
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    82
    +0.13
    0.03
    38
    +0.12
    0.01
    59
    +0.11
    0.01
    Negative Logits
    pbio
    -1.61
    pcbi
    -1.52
    )|^
    -1.50
    Conclusion
    -1.46
     lately
    -1.43
    ccoli
    -1.38
     plasm
    -1.34
     Twitter
    -1.30
     CAG
    -1.26
    pmed
    -1.25
    POSITIVE LOGITS
    ities
    1.73
     itself
    1.64
    est
    1.47
    hood
    1.46
    ersion
    1.44
     solely
    1.44
     yourself
    1.43
    ÃŁe
    1.42
    ette
    1.42
     \[*
    1.40
    Activations Density 0.455%

    No Known Activations