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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 27186
    Prev
    Next
    INDEX
    Explanations

    mentions of rural or small communities

    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
    +0.30
    1.9%
    330
    +0.14
    0.9%
    247
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    330
    +0.30
    0.01
    156
    +0.14
    0.01
    180
    +0.10
    0.01
    Negative Logits
    ĥ½
    -1.67
    fered
    -1.67
     gay
    -1.59
    ľ
    -1.57
     sexes
    -1.54
     latter
    -1.54
    Ń
    -1.52
    Ŀ
    -1.52
    ↵
    -1.51
     ↵
    -1.51
    POSITIVE LOGITS
    heet
    2.10
    etter
    2.01
    hell
    1.91
    ystems
    1.72
    etable
    1.70
    weet
    1.66
    ocs
    1.59
    creen
    1.56
    erver
    1.56
    enda
    1.53
    Activations Density 0.104%

    No Known Activations