© 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. 0-MLP-SM
    11. 29377
    Prev
    Next
    INDEX
    Explanations

    the word "dealt."

    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
    111
    +0.15
    0.8%
    387
    +0.13
    0.8%
    372
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    372
    +0.15
    0.01
    387
    +0.13
    0.01
    263
    +0.12
    0.01
    Negative Logits
    ´
    -1.78
    °
    -1.60
    µ
    -1.55
    ĩ
    -1.52
     Spacewatch
    -1.46
     slightest
    -1.40
    Ľ
    -1.39
    ·
    -1.37
    Ħ
    -1.37
     recorded
    -1.37
    POSITIVE LOGITS
    heet
    1.71
    bian
    1.68
    thal
    1.64
    mith
    1.61
    sci
    1.56
    chool
    1.54
     beforehand
    1.53
    pn
    1.49
    iate
    1.47
    nier
    1.47
    Activations Density 1.345%

    No Known Activations