© 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
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. MLP Post
    5. 2-MLP-SM
    6. 25799
    Prev
    Next
    INDEX
    Explanations

    legal terms and mentions of liability in 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
    156
    +0.26
    1.5%
    17
    +0.12
    0.7%
    386
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    501
    +0.26
    0.06
    38
    +0.12
    -0.01
    97
    +0.10
    0.03
    Negative Logits
    wards
    -1.77
    ward
    -1.73
    ially
    -1.72
    mediately
    -1.54
    istically
    -1.52
    ()</
    -1.52
     further
    -1.48
     downstream
    -1.48
    atively
    -1.47
    forth
    -1.46
    POSITIVE LOGITS
    ©
    2.46
    ±
    2.36
    ª
    2.35
    ĥ
    2.30
    ½
    2.27
    §
    2.17
    ¡
    2.17
    «
    2.15
    ¢
    2.11
    ĨĴ
    2.10
    Activations Density 1.265%

    No Known Activations