© 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. 24324
    Prev
    Next
    INDEX
    Explanations

    numerical values and decimal points

    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
    96
    +0.11
    0.6%
    92
    +0.11
    0.6%
    200
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    497
    +0.11
    0.01
    400
    +0.11
    0.03
    231
    +0.10
    0.03
    Negative Logits
     Lanka
    -1.49
     lately
    -1.49
     inhabited
    -1.48
     hitherto
    -1.46
     Stores
    -1.45
    :"
    -1.45
    ONS
    -1.41
     inbox
    -1.39
     evacuated
    -1.39
     commanded
    -1.30
    POSITIVE LOGITS
    ľ
    2.29
    Ľ
    2.26
    ©
    2.24
    ¿
    2.04
    ķ
    1.94
    IJ
    1.92
    Ń
    1.91
    ĸ´
    1.84
    ĺ
    1.74
    ¾
    1.73
    Activations Density 0.218%

    No Known Activations