© 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. 24698
    Prev
    Next
    INDEX
    Explanations

    technical descriptions and specifications related to devices or systems

    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
    126
    +0.14
    0.8%
    431
    +0.11
    0.6%
    6
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    402
    +0.14
    0.03
    497
    +0.11
    -0.00
    314
    +0.10
    0.03
    Negative Logits
    Ħ
    -4.34
    ĩ
    -4.23
    Ĥ
    -4.21
    ĻĤ
    -4.17
    ģ
    -3.89
    »¿
    -3.78
    ĭ
    -3.77
    ħ
    -3.72
    ĥ
    -3.72
    ½
    -3.72
    POSITIVE LOGITS
    ijan
    1.38
    asone
    1.35
    alion
    1.33
    itto
    1.32
    nih
    1.32
    ipel
    1.31
     finale
    1.30
    adoc
    1.29
    ESH
    1.29
     anytime
    1.29
    Activations Density 0.362%

    No Known Activations