© 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. 26002
    Prev
    Next
    INDEX
    Explanations

    mentions of vaccination and related health concepts

    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
    410
    +0.17
    1.0%
    511
    +0.14
    0.8%
    111
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.17
    0.02
    59
    +0.14
    0.01
    321
    +0.14
    0.01
    Negative Logits
    »
    -3.53
    ľĵ
    -3.43
    ·¸
    -3.42
    ĨĴ
    -3.41
    -3.36
    č↵
    -3.36
    -3.36
    <|outofrange|>
    -3.36
     ↵
    -3.36
    ↵↵
    -3.36
    POSITIVE LOGITS
    idium
    1.93
    gos
    1.61
    nor
    1.60
    chin
    1.46
    sty
    1.46
     hearing
    1.42
    iative
    1.41
    ryl
    1.40
    enance
    1.39
    rant
    1.36
    Activations Density 0.008%

    No Known Activations