© 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. 30047
    Prev
    Next
    INDEX
    Explanations

    instances of the contraction "I'd" indicating a past intention or action

    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
    112
    +0.13
    0.7%
    257
    +0.12
    0.7%
    58
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    338
    +0.13
    0.06
    402
    +0.12
    0.05
    223
    +0.12
    0.05
    Negative Logits
    imes
    -1.78
     balance
    -1.45
    MAP
    -1.42
    kins
    -1.38
    yy
    -1.38
    Competing
    -1.37
     ')
    -1.33
    wed
    -1.33
     distinction
    -1.31
     homeostasis
    -1.30
    POSITIVE LOGITS
    ĭ
    2.57
    ı
    2.55
    Ī
    2.47
    ī
    2.46
    Ł
    2.45
    į
    2.42
    Ľ
    2.39
    IJ
    2.32
    §
    2.31
    ½
    2.25
    Activations Density 0.112%

    No Known Activations