© 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. 25535
    Prev
    Next
    INDEX
    Explanations

    references to specific brands or companies involved in the cannabis industry

    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
    369
    +0.15
    0.9%
    325
    +0.14
    0.8%
    7
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.15
    0.01
    7
    +0.14
    0.01
    71
    +0.12
    0.01
    Negative Logits
    lando
    -1.58
    ances
    -1.53
    ears
    -1.47
    ocytes
    -1.45
    xture
    -1.44
    FORMATION
    -1.39
     Prior
    -1.39
    ETHOD
    -1.35
     other
    -1.34
    ities
    -1.34
    POSITIVE LOGITS
    ious
    1.77
    ulence
    1.73
    ulent
    1.68
    witz
    1.64
    bow
    1.62
    holm
    1.60
    stadt
    1.59
    stein
    1.54
     ethic
    1.52
    idone
    1.52
    Activations Density 0.015%

    No Known Activations