© 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. 22911
    Prev
    Next
    INDEX
    Explanations

    links to specific individuals or groups

    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
    436
    +0.13
    0.8%
    272
    +0.13
    0.7%
    213
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    284
    +0.13
    0.05
    217
    +0.13
    0.12
    272
    +0.12
    0.10
    Negative Logits
    ermost
    -1.63
    same
    -1.59
    estry
    -1.47
     dividing
    -1.45
     above
    -1.45
     portion
    -1.42
    osphere
    -1.40
    .“
    -1.40
     Turks
    -1.40
     foregoing
    -1.39
    POSITIVE LOGITS
    izable
    1.60
    '>
    1.46
     fav
    1.45
     jeans
    1.44
    watson
    1.43
    attr
    1.42
    '">
    1.40
    itis
    1.36
    umab
    1.35
    umber
    1.34
    Activations Density 2.449%

    No Known Activations