© 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. 2-MLP-SM
    11. 23717
    Prev
    Next
    INDEX
    Explanations

    phrases indicating changes in emotional states or well-being

    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
    21
    +0.12
    0.7%
    439
    +0.10
    0.6%
    376
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    130
    +0.12
    0.15
    182
    +0.10
    0.14
    21
    +0.10
    0.08
    Negative Logits
    ching
    -1.66
     careful
    -1.63
     clear
    -1.60
    rying
    -1.59
     heart
    -1.58
     tough
    -1.57
     oxygen
    -1.54
     critical
    -1.48
     intervals
    -1.44
    ys
    -1.43
    POSITIVE LOGITS
    ág
    2.00
    #:
    1.95
    heet
    1.90
    rams
    1.75
     msgid
    1.75
    ournal
    1.73
    enda
    1.69
    CRIPT
    1.67
    heets
    1.67
    papers
    1.65
    Activations Density 1.611%

    No Known Activations