© 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. 23333
    Prev
    Next
    INDEX
    Explanations

    patterns related to the passage of time and motion in contexts involving change or transitions

    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
    +0.56
    4.3%
    111
    +0.49
    3.7%
    222
    +0.08
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    467
    +0.56
    0.00
    5
    +0.49
    0.00
    159
    +0.08
    0.00
    Negative Logits
    1451450014514500
    -1.36
    )}}\
    -1.20
    ductive
    -1.20
    )$)
    -1.14
    ==============================
    -1.14
    ==================================
    -1.13
    ))\
    -1.12
    \,$
    -1.11
    ========================
    -1.10
     JJ
    -1.07
    POSITIVE LOGITS
    ĨĴ
    1.81
    Ń
    1.62
    ³
    1.61
    ¢
    1.52
    »¿
    1.51
    ij
    1.49
    º
    1.44
    ĵ
    1.44
    ±
    1.44
    Ļª
    1.42
    Activations Density 0.018%

    No Known Activations