© 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. 29715
    Prev
    Next
    INDEX
    Explanations

    references to citizenship and related 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
    156
    +0.24
    1.4%
    232
    +0.12
    0.7%
    122
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.24
    0.01
    122
    +0.12
    0.01
    324
    +0.11
    0.01
    Negative Logits
    Ĥ¬
    -3.75
    ĥ½
    -3.55
    ↵
    -3.53
    -3.53
    ↵
    -3.53
    -3.53
    ↵            ↵
    -3.53
    -3.53
    ↵Č
    -3.53
    <|outofrange|>
    -3.53
    POSITIVE LOGITS
    ium
    2.11
    atics
    1.89
     bases
    1.70
    ato
    1.67
    ry
    1.66
     remains
    1.57
     behind
    1.55
    liness
    1.53
     quarters
    1.53
    !(
    1.52
    Activations Density 0.012%

    No Known Activations