© 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. 26324
    Prev
    Next
    INDEX
    Explanations

    the act of prioritizing tasks or issues

    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
    376
    +0.19
    1.1%
    59
    +0.13
    0.8%
    29
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    59
    +0.19
    0.01
    344
    +0.13
    0.01
    330
    +0.12
    0.01
    Negative Logits
    fulness
    -1.75
    fficients
    -1.69
    à±ģ
    -1.63
    ful
    -1.56
     chance
    -1.46
    fully
    -1.46
    bone
    -1.41
    llo
    -1.38
    ness
    -1.38
     multiplicative
    -1.36
    POSITIVE LOGITS
    ĻĤ
    1.90
    ¤
    1.84
    Ģ
    1.79
    Ĩ
    1.71
    £
    1.68
    ·
    1.61
    eto
    1.53
    agon
    1.53
    ©
    1.50
    aea
    1.49
    Activations Density 0.016%

    No Known Activations