© 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. 27735
    Prev
    Next
    INDEX
    Explanations

    instances of the word "on"

    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
    312
    +0.11
    0.6%
    396
    +0.11
    0.6%
    421
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    69
    +0.11
    0.22
    152
    +0.11
    0.17
    47
    +0.11
    0.15
    Negative Logits
    ¾
    -2.37
    Ŀ
    -2.16
    ĺ
    -2.11
    ¶
    -1.99
    Ľ
    -1.96
    ĵ
    -1.95
    ĥ½
    -1.95
    ı
    -1.91
    Ń
    -1.88
    ļ
    -1.83
    POSITIVE LOGITS
    sec
    1.35
     refer
    1.33
    Song
    1.33
     monitors
    1.28
    dec
    1.27
    EMA
    1.26
    days
    1.25
    disambiguation
    1.25
    charts
    1.25
     chant
    1.24
    Activations Density 0.440%

    No Known Activations