© 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. 24136
    Prev
    Next
    INDEX
    Explanations

    specific numerical data or statistics

    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%
    170
    +0.14
    0.8%
    33
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    159
    +0.15
    0.02
    302
    +0.14
    0.04
    402
    +0.12
    0.03
    Negative Logits
     ages
    -1.85
    ties
    -1.61
     insertions
    -1.47
    edia
    -1.43
    brains
    -1.38
     locations
    -1.38
    agers
    -1.37
     starters
    -1.36
    wed
    -1.35
     laptops
    -1.33
    POSITIVE LOGITS
    ½
    3.69
    ³
    3.30
    ·¸
    3.22
    ¨
    3.20
    ¿
    3.13
    ²
    3.03
    ¶
    3.02
    ¿½
    3.00
    IJ
    2.93
    ķ
    2.82
    Activations Density 0.182%

    No Known Activations