© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 30127
    Prev
    Next
    INDEX
    Explanations

    repeated expressions of an intense emotional state or sentiment

    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
    51
    +0.15
    0.8%
    492
    +0.13
    0.7%
    332
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    471
    +0.15
    0.05
    437
    +0.13
    0.04
    187
    +0.12
    0.05
    Negative Logits
    ests
    -1.68
     league
    -1.65
    ual
    -1.65
    esters
    -1.62
    ishers
    -1.61
     retailers
    -1.59
    erate
    -1.54
    ester
    -1.52
     merchants
    -1.51
    isher
    -1.48
    POSITIVE LOGITS
    psy
    1.68
    ī
    1.67
    inous
    1.66
     âĢł
    1.66
    ère
    1.59
    berger
    1.53
    enne
    1.50
    apine
    1.45
    gnu
    1.45
    essen
    1.44
    Activations Density 0.054%

    No Known Activations