© 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. 27740
    Prev
    Next
    INDEX
    Explanations

    expressions of significant emphasis or urgency

    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
    23
    +0.26
    1.5%
    478
    +0.20
    1.2%
    203
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    294
    +0.26
    0.02
    307
    +0.20
    0.02
    278
    +0.12
    0.02
    Negative Logits
    ista
    -1.85
     alike
    -1.67
    mare
    -1.62
    iast
    -1.61
    icio
    -1.59
    mates
    -1.59
    ,
    -1.58
    acia
    -1.57
    iazep
    -1.54
    iste
    -1.53
    POSITIVE LOGITS
    ĥ½
    3.26
    ı
    2.76
    Ļª
    2.73
    į
    2.61
    Į
    2.52
    ĩ
    2.48
    º
    2.46
    ĻĤ
    2.42
    Ĩ
    2.39
    ´
    2.39
    Activations Density 0.702%

    No Known Activations