© 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. 25470
    Prev
    Next
    INDEX
    Explanations

    the word "welcome" or similar welcoming phrases

    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
    376
    +0.20
    1.1%
    38
    +0.15
    0.8%
    339
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    339
    +0.20
    0.02
    38
    +0.15
    0.02
    408
    +0.13
    0.02
    Negative Logits
    ITC
    -1.61
    inx
    -1.54
    imer
    -1.49
    ronic
    -1.48
    Appellee
    -1.45
    unnumbered
    -1.45
    ymers
    -1.45
    PI
    -1.44
    ching
    -1.44
    tw
    -1.37
    POSITIVE LOGITS
    ½
    1.66
    ł
    1.57
    ī
    1.53
     sounds
    1.45
     voc
    1.44
    ¾
    1.43
     calling
    1.43
    ģ
    1.43
    ently
    1.42
     responsibility
    1.39
    Activations Density 0.036%

    No Known Activations