© 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. 22741
    Prev
    Next
    INDEX
    Explanations

    references to software licenses

    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
    452
    +0.11
    0.6%
    5
    +0.10
    0.6%
    269
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    103
    +0.11
    0.02
    452
    +0.10
    0.01
    0
    +0.10
    0.02
    Negative Logits
    fony
    -1.59
    fork
    -1.59
    starter
    -1.56
    forge
    -1.55
    bsd
    -1.48
     fund
    -1.45
    mith
    -1.41
     fork
    -1.41
    ylase
    -1.41
    brew
    -1.40
    POSITIVE LOGITS
    ings
    2.23
    ĻĤ
    1.97
    ī
    1.94
    Ĩ
    1.93
    ¡
    1.90
    ĨĴ
    1.85
    Ĥ¬
    1.84
    ³
    1.82
    Ļª
    1.82
    ²
    1.81
    Activations Density 0.095%

    No Known Activations