© 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 EvalsExportsinterp-engineNEWAPI 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. 24152
    Prev
    Next
    INDEX
    Explanations

    website and blogging platform references

    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
    241
    +0.12
    0.7%
    123
    +0.10
    0.6%
    306
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    241
    +0.12
    0.02
    125
    +0.10
    0.03
    50
    +0.10
    0.01
    Negative Logits
    quo
    -1.60
    rugs
    -1.59
    football
    -1.39
    ESULT
    -1.38
     nud
    -1.37
    *âĢIJ
    -1.37
    ollow
    -1.37
     flags
    -1.36
    ustr
    -1.36
     clearly
    -1.35
    POSITIVE LOGITS
    Ļª
    1.70
    hest
    1.57
              ↵
    1.55
    ↵
    1.55
    1.55
    1.55
    1.55
    č↵
    1.55
          ↵
    1.55
    ↵
    1.55
    Activations Density 0.242%

    No Known Activations