© 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. 0-MLP-SM
    11. 29990
    Prev
    Next
    INDEX
    Explanations

    terms related to mathematics and mathematical concepts

    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/0-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.0.hook_mlp_out
    Hook Layer
    0
    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
    447
    +0.11
    0.6%
    376
    +0.10
    0.6%
    468
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    447
    +0.11
    0.01
    328
    +0.10
    0.01
    468
    +0.10
    0.01
    Negative Logits
    ¯
    -2.62
    ĥ
    -2.46
    Īĺ
    -2.28
    ·¸
    -2.18
    ¬
    -2.13
    ¿½
    -2.03
    ½
    -2.03
    Ĭ
    -2.02
    ¸
    -1.97
    Ĥ
    -1.89
    POSITIVE LOGITS
    ieu
    1.82
    tech
    1.71
    hematic
    1.70
    aceut
    1.65
    TeX
    1.65
    ÃŃvel
    1.64
    érie
    1.62
    âĤ¬
    1.60
    ilde
    1.58
    ieval
    1.55
    Activations Density 3.633%

    No Known Activations