© 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. 2-MLP-SM
    11. 24293
    Prev
    Next
    INDEX
    Explanations

    legal terms and conditions often related to agreements or contracts

    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/2-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.2.hook_mlp_out
    Hook Layer
    2
    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
    500
    +0.14
    0.8%
    395
    +0.14
    0.7%
    465
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    33
    +0.14
    0.10
    466
    +0.14
    0.14
    178
    +0.13
    0.14
    Negative Logits
     ([@
    -1.70
     Weber
    -1.69
    .^[@
    -1.59
    ,^[@
    -1.55
     renewal
    -1.51
     competition
    -1.44
    nier
    -1.42
    er
    -1.42
    ister
    -1.40
    ptic
    -1.38
    POSITIVE LOGITS
    $.[]{
    1.84
    $]{};
    1.70
    ĨĴ
    1.64
    ↵
    1.58
    1.58
    1.58
    <|outofrange|>
    1.58
    ↵
    1.58
    1.58
    <|outofrange|>
    1.58
    Activations Density 4.494%

    No Known Activations