© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 27959
    Prev
    Next
    INDEX
    Explanations

    instances of the word "lot" and its variations

    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
    +0.16
    0.9%
    53
    +0.14
    0.8%
    409
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    409
    +0.16
    0.05
    42
    +0.14
    0.05
    34
    +0.13
    0.05
    Negative Logits
     Plaintiffs
    -1.86
     slightest
    -1.80
     plaintiffs
    -1.70
    ____________
    -1.69
     least
    -1.64
     entire
    -1.54
    least
    -1.48
     millions
    -1.48
     strongest
    -1.47
    odor
    -1.47
    POSITIVE LOGITS
    ģ
    3.67
    ¿½
    3.63
    Īĺ
    3.63
    ī
    3.63
    °
    3.57
    İ
    3.52
    ķ
    3.48
    »¿
    3.46
    Ģ
    3.41
    ½
    3.34
    Activations Density 0.716%

    No Known Activations