© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 25265
    Prev
    Next
    INDEX
    Explanations

    terms related to living conditions and lifestyle

    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
    +0.13
    0.7%
    221
    +0.12
    0.7%
    275
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    275
    +0.13
    0.00
    221
    +0.12
    0.01
    163
    +0.12
    0.01
    Negative Logits
    ivism
    -1.67
    *](#
    -1.63
    starter
    -1.60
    FIL
    -1.56
    ivist
    -1.54
    imedia
    -1.54
    hdad
    -1.52
    ãĢĢãĢĢ
    -1.52
    negie
    -1.51
    ugu
    -1.51
    POSITIVE LOGITS
    hes
    1.73
    nan
    1.59
    ¿½
    1.59
     slightest
    1.54
     corners
    1.52
    ¾
    1.48
    ¸
    1.45
    rops
    1.45
     shear
    1.45
    Ŀ
    1.44
    Activations Density 0.054%

    No Known Activations