© 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. 30589
    Prev
    Next
    INDEX
    Explanations

    occurrences of the term "Update" in various contexts

    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
    156
    +0.25
    1.4%
    376
    +0.20
    1.2%
    392
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    126
    +0.25
    0.01
    392
    +0.20
    0.01
    454
    +0.12
    0.01
    Negative Logits
    Ĵ
    -2.82
    ĥ½
    -2.63
    Ī
    -2.63
    ©
    -2.49
    ĭ
    -2.43
    Ļª
    -2.32
    §
    -2.29
    ¯
    -2.27
     ↵
    -2.23
    -2.23
    POSITIVE LOGITS
    ding
    1.88
    manship
    1.74
    zilla
    1.65
    ulent
    1.63
    cule
    1.49
    pread
    1.41
    generation
    1.40
    etine
    1.39
    Guard
    1.37
    ions
    1.34
    Activations Density 0.007%

    No Known Activations