© 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. 26369
    Prev
    Next
    INDEX
    Explanations

    references to massage therapy

    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
    156
    +0.26
    1.6%
    376
    +0.14
    0.8%
    71
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    442
    +0.26
    0.01
    26
    +0.14
    0.01
    349
    +0.12
    0.01
    Negative Logits
     hers
    -1.80
    woke
    -1.71
    ĥ
    -1.71
     yours
    -1.66
    į
    -1.56
    ppers
    -1.50
     sweat
    -1.50
    aked
    -1.47
    ird
    -1.46
     miscar
    -1.46
    POSITIVE LOGITS
    ENTIAL
    1.70
    ctx
    1.67
    nikov
    1.58
    ulent
    1.58
    caster
    1.56
     toward
    1.55
    expr
    1.55
     duties
    1.53
     aside
    1.50
     than
    1.47
    Activations Density 0.021%

    No Known Activations