© 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. 23157
    Prev
    Next
    INDEX
    Explanations

    instances of the word "but," indicating a focus on contrasts or exceptions within the text

    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
    274
    +0.13
    0.7%
    466
    +0.10
    0.6%
    266
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    274
    +0.13
    0.08
    182
    +0.10
    0.07
    502
    +0.10
    0.07
    Negative Logits
    ¿½
    -2.92
    Ĺ
    -2.63
    ķ
    -2.59
    ĻĤ
    -2.56
    ĵ
    -2.41
    Ļª
    -2.36
    ¿
    -2.32
    ¨
    -2.17
    Ķ
    -2.17
    Ĥ¬
    -2.14
    POSITIVE LOGITS
    heets
    1.74
    izer
    1.57
    ugu
    1.46
    aintiff
    1.43
    ypse
    1.43
    anguage
    1.42
     possession
    1.40
     "",
    1.40
    ize
    1.36
    spacing
    1.34
    Activations Density 0.257%

    No Known Activations