© 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. 25982
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate declarations or statements made by individuals

    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
    +0.23
    1.3%
    115
    +0.16
    0.9%
    503
    +0.15
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    503
    +0.23
    0.03
    273
    +0.16
    0.03
    364
    +0.15
    0.03
    Negative Logits
    ĥ½
    -2.13
    ↵↵
    -1.84
    <|outofrange|>
    -1.84
    ↵
    -1.84
    ↵
    -1.84
    ↵
    -1.84
    ↵
    -1.84
    ↵
    -1.84
    -1.84
    ↵
    -1.84
    POSITIVE LOGITS
    protect
    1.50
    oche
    1.40
    above
    1.38
     order
    1.35
    family
    1.34
    trunc
    1.33
    below
    1.30
     boundaries
    1.30
    triangle
    1.29
     Tort
    1.28
    Activations Density 0.024%

    No Known Activations