© 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 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. 24483
    Prev
    Next
    INDEX
    Explanations

    patterns of speech, especially those that indicate emotional expressions or attitudes

    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
    422
    +0.11
    0.6%
    233
    +0.11
    0.6%
    369
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    60
    +0.11
    0.05
    423
    +0.11
    0.10
    376
    +0.10
    0.07
    Negative Logits
    ---|---
    -1.76
    aps
    -1.69
    ---|---|---
    -1.44
    versed
    -1.42
    idan
    -1.41
    ipher
    -1.39
    description
    -1.39
    athering
    -1.38
    ../
    -1.35
    icipants
    -1.35
    POSITIVE LOGITS
    Į
    2.81
    «
    2.73
    ¦
    2.66
    ¼
    2.61
    ¸
    2.58
    ĸ´
    2.50
    ³
    2.46
    ī
    2.45
    Ŀ
    2.45
    º
    2.43
    Activations Density 1.050%

    No Known Activations