© 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. 23970
    Prev
    Next
    INDEX
    Explanations

    numerical values related to mathematical operations, especially roots and powers

    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
    31
    +0.13
    0.7%
    405
    +0.12
    0.7%
    146
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    31
    +0.13
    0.03
    405
    +0.12
    0.03
    435
    +0.11
    0.02
    Negative Logits
    ª
    -2.45
    ¬
    -2.37
    ī
    -2.34
    ĩ
    -2.31
    ¿½
    -2.26
    ¶
    -2.23
    ±
    -2.20
    ĥ
    -2.15
    ¨
    -2.10
    ½
    -2.10
    POSITIVE LOGITS
    uum
    1.44
    ypse
    1.41
    thro
    1.39
    LEX
    1.37
    nikov
    1.37
    eles
    1.34
    ient
    1.32
     damn
    1.28
    FROM
    1.28
    utton
    1.27
    Activations Density 0.143%

    No Known Activations