© 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. 23268
    Prev
    Next
    INDEX
    Explanations

    references to software libraries and programming components

    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
    +0.19
    1.1%
    289
    +0.12
    0.7%
    207
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    135
    +0.19
    0.03
    390
    +0.12
    0.02
    30
    +0.12
    0.02
    Negative Logits
    others
    -1.49
    kees
    -1.46
    idays
    -1.46
    asan
    -1.44
    ux
    -1.44
    isin
    -1.43
    kers
    -1.41
    foreign
    -1.39
     sense
    -1.38
    chten
    -1.37
    POSITIVE LOGITS
    §
    3.16
    ĨĴ
    3.11
    ¾
    2.96
    Ļª
    2.94
    ı
    2.86
    İ
    2.85
    2.79
    2.79
     ↵
    2.79
    2.79
    Activations Density 1.351%

    No Known Activations