© 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. 27131
    Prev
    Next
    INDEX
    Explanations

    mentions of the title "Vice President."

    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
    221
    +0.13
    0.7%
    102
    +0.13
    0.7%
    469
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    102
    +0.13
    0.02
    469
    +0.13
    0.02
    221
    +0.11
    0.02
    Negative Logits
     anything
    -2.04
     penalties
    -1.75
     harm
    -1.67
     harmed
    -1.65
     similarly
    -1.57
     overtime
    -1.57
     otherwise
    -1.56
     face
    -1.53
     emotion
    -1.52
     sweat
    -1.52
    POSITIVE LOGITS
    ulent
    1.97
     versa
    1.89
    zilla
    1.83
    hua
    1.82
    ious
    1.80
    "}](#
    1.78
    leys
    1.71
    wave
    1.68
    horn
    1.66
    craft
    1.66
    Activations Density 0.188%

    No Known Activations