© 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. 2-MLP-SM
    11. 26390
    Prev
    Next
    INDEX
    Explanations

    references to children and their well-being

    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/2-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.2.hook_mlp_out
    Hook Layer
    2
    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
    170
    +0.15
    0.8%
    23
    +0.12
    0.7%
    134
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    235
    +0.15
    0.05
    141
    +0.12
    0.04
    31
    +0.12
    0.04
    Negative Logits
    ı
    -3.11
    ¾
    -3.01
    Ļ
    -3.00
    º
    -2.96
    «
    -2.94
    Ľ
    -2.93
    Į
    -2.91
    İ
    -2.84
    ģ
    -2.79
    ³
    -2.79
    POSITIVE LOGITS
    forall
    1.52
    substack
    1.52
     \$
    1.50
    reon
    1.49
    valence
    1.47
    rl
    1.45
    retched
    1.45
    |}\
    1.44
     Allah
    1.42
    compare
    1.41
    Activations Density 0.451%

    No Known Activations