© 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. 26917
    Prev
    Next
    INDEX
    Explanations

    references to specific entities, particularly in the context of legal or formal documents

    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
    23
    +0.21
    1.2%
    63
    +0.12
    0.7%
    498
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    23
    +0.21
    0.06
    458
    +0.12
    0.06
    306
    +0.11
    0.06
    Negative Logits
    GREEK
    -1.60
    lan
    -1.60
     brakes
    -1.48
    obo
    -1.44
     Luxem
    -1.42
    overview
    -1.41
     himself
    -1.40
     Collaboration
    -1.37
    endi
    -1.37
    weight
    -1.36
    POSITIVE LOGITS
    Ĺ
    2.57
    ŀ
    2.40
    ľĵ
    2.18
    ķ
    2.11
    ¢
    2.05
    ®
    2.00
    ¿½
    1.92
    ¥
    1.91
    ¯
    1.90
    ±
    1.89
    Activations Density 1.895%

    No Known Activations