© 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. 25050
    Prev
    Next
    INDEX
    Explanations

    mentions of decisions

    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
    +0.15
    0.8%
    172
    +0.12
    0.7%
    243
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    46
    +0.15
    0.04
    243
    +0.12
    0.04
    120
    +0.12
    0.04
    Negative Logits
    Ļ
    -3.16
    ³
    -3.09
    ĥ½
    -3.06
    Ĺ
    -2.91
    ¿½
    -2.88
    Ł
    -2.78
    ¹
    -2.77
    ¤
    -2.76
    ±
    -2.74
    §
    -2.70
    POSITIVE LOGITS
    oles
    1.66
     corner
    1.54
     elsewhere
    1.40
    /
    1.39
    cat
    1.37
     unnecessary
    1.33
    ---|---
    1.31
     âĢķ
    1.31
    lining
    1.31
     void
    1.30
    Activations Density 0.503%

    No Known Activations