© 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. 23968
    Prev
    Next
    INDEX
    Explanations

    expressions of strong emotions or significant experiences

    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
    +0.70
    5.3%
    111
    +0.19
    1.5%
    353
    +0.09
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    376
    +0.70
    0.07
    495
    +0.19
    0.07
    353
    +0.09
    0.06
    Negative Logits
    ↵
    -5.16
    č↵
    -5.16
    -5.16
    ↵
    -5.16
     ↵
    -5.16
    ↵    ↵
    -5.16
    ↵  ↵
    -5.16
    -5.16
    -5.16
    ↵↵
    -5.16
    POSITIVE LOGITS
    ulated
    1.49
    hardt
    1.36
    osi
    1.33
    heim
    1.33
    rette
    1.31
     anymore
    1.29
    witz
    1.21
    elles
    1.18
    rem
    1.17
     against
    1.16
    Activations Density 0.393%

    No Known Activations