© 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. 24756
    Prev
    Next
    INDEX
    Explanations

    code structures and syntax elements

    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
    342
    +0.13
    0.7%
    61
    +0.12
    0.7%
    500
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    122
    +0.13
    0.02
    386
    +0.12
    0.01
    61
    +0.10
    0.03
    Negative Logits
    lessly
    -1.77
    ?**
    -1.55
     shared
    -1.55
    ages
    -1.52
    tti
    -1.50
     pipelines
    -1.46
     specifically
    -1.44
     even
    -1.42
     ours
    -1.40
     developing
    -1.40
    POSITIVE LOGITS
    Ļ
    2.18
    £
    1.93
    ī
    1.93
    ĥ
    1.87
    ¿½
    1.82
    Ĩ
    1.80
    ħ
    1.79
    ¡
    1.74
    Į
    1.74
    »¿
    1.74
    Activations Density 0.388%

    No Known Activations