© 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. 2-MLP-SM
    11. 25819
    Prev
    Next
    INDEX
    Explanations

    phrases indicating existence, presence, or assessment of conditions

    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
    399
    +0.12
    0.7%
    27
    +0.12
    0.7%
    192
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    323
    +0.12
    0.05
    69
    +0.12
    0.06
    231
    +0.12
    0.07
    Negative Logits
    ĩ
    -2.24
    ĥ
    -1.89
    Ń
    -1.88
     CAG
    -1.74
    ²
    -1.69
    Ĩ
    -1.69
    ¼
    -1.68
    ī
    -1.53
    §
    -1.52
     honour
    -1.49
    POSITIVE LOGITS
    ppat
    1.67
    pgen
    1.55
    isten
    1.52
     ³³ ³³ ³³ ³³
    1.46
    paper
    1.45
    pmed
    1.43
    ptions
    1.43
    pntd
    1.41
    ↵
    1.38
    IRS
    1.36
    Activations Density 1.007%

    No Known Activations