© 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. 30749
    Prev
    Next
    INDEX
    Explanations

    terms related to stakeholder involvement and participation

    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
    108
    +0.15
    0.8%
    376
    +0.13
    0.8%
    323
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    323
    +0.15
    0.01
    108
    +0.13
    0.01
    73
    +0.12
    0.01
    Negative Logits
    ĨĴ
    -5.47
    ↵
    -5.28
    ↵↵↵
    -5.28
    -5.28
    ↵
    -5.28
    č↵č↵
    -5.28
    -5.28
    <|outofrange|>
    -5.28
    č↵
    -5.28
    -5.28
    POSITIVE LOGITS
    iors
    2.26
    ariate
    1.84
    stown
    1.84
    ial
    1.83
    ive
    1.78
     controls
    1.73
     powers
    1.71
     senses
    1.70
    erate
    1.70
     measures
    1.67
    Activations Density 0.018%

    No Known Activations