© 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 EvalsExportsAPI 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. 28788
    Prev
    Next
    INDEX
    Explanations

    strings representing authentication tokens

    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
    +0.14
    0.8%
    406
    +0.11
    0.6%
    162
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    406
    +0.14
    0.01
    126
    +0.11
    0.01
    371
    +0.10
    0.01
    Negative Logits
    ı
    -3.19
    ĥ½
    -2.97
    Īĺ
    -2.94
    -2.90
    ↵
    -2.90
    ↵
    -2.90
    ↵
    -2.90
    č↵
    -2.90
    <|outofrange|>
    -2.90
    <|outofrange|>
    -2.90
    POSITIVE LOGITS
    ENTIAL
    1.83
    etto
    1.82
    volt
    1.78
    ific
    1.73
    shot
    1.71
    istas
    1.71
    fonts
    1.62
    bon
    1.62
    assic
    1.58
    aho
    1.55
    Activations Density 0.016%

    No Known Activations