© 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. 24418
    Prev
    Next
    INDEX
    Explanations

    descriptions of tourism and historical sites

    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
    319
    +0.16
    0.9%
    419
    +0.13
    0.8%
    296
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    296
    +0.16
    0.10
    255
    +0.13
    0.09
    14
    +0.13
    0.09
    Negative Logits
    liest
    -1.57
     rains
    -1.54
    aign
    -1.54
    aths
    -1.51
     hereditary
    -1.50
     nearby
    -1.46
    ÃŁe
    -1.46
     shadows
    -1.45
     winds
    -1.45
    iest
    -1.44
    POSITIVE LOGITS
    ¦
    1.94
    ↵
    1.64
    ↵
    1.64
    1.64
    č↵
    1.64
    ↵↵
    1.64
     ↵
    1.64
    ↵
    1.64
    ↵
    1.64
     ↵
    1.64
    Activations Density 1.509%

    No Known Activations