© 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. 28415
    Prev
    Next
    INDEX
    Explanations

    instances of the word "Control" and its variations in various contexts

    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
    +0.18
    1.0%
    451
    +0.15
    0.8%
    156
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    451
    +0.18
    0.02
    461
    +0.15
    0.01
    14
    +0.14
    0.01
    Negative Logits
     comrades
    -1.68
     mourning
    -1.62
     psychiatric
    -1.60
     antidepress
    -1.58
    lings
    -1.56
    soever
    -1.49
    nings
    -1.45
     ever
    -1.43
     fair
    -1.42
    selves
    -1.41
    POSITIVE LOGITS
    assic
    1.73
    ément
    1.73
    icolor
    1.69
     booth
    1.63
    anne
    1.59
    tera
    1.50
    box
    1.50
    ÃŃc
    1.48
     era
    1.48
    iva
    1.47
    Activations Density 0.007%

    No Known Activations