© 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 EvalsExportsAPI 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. 24524
    Prev
    Next
    INDEX
    Explanations

    mathematical concepts related to summation

    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
    +0.13
    0.7%
    114
    +0.13
    0.7%
    109
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    151
    +0.13
    0.06
    212
    +0.13
    0.05
    109
    +0.12
    0.05
    Negative Logits
    FROM
    -1.50
    osome
    -1.50
    .+
    -1.49
    EventArgs
    -1.42
    ité
    -1.41
    ocene
    -1.41
    coupled
    -1.41
     characterized
    -1.38
    affinity
    -1.38
    reek
    -1.36
    POSITIVE LOGITS
    adas
    1.58
    istas
    1.52
    eral
    1.50
     Side
    1.47
    eves
    1.46
    olds
    1.44
    posts
    1.41
    igos
    1.39
    ums
    1.36
    ermal
    1.36
    Activations Density 1.078%

    No Known Activations