© 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. 2-MLP-SM
    11. 25166
    Prev
    Next
    INDEX
    Explanations

    references to the concept of "original" in various contexts

    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
    179
    +0.14
    0.8%
    244
    +0.13
    0.7%
    14
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    179
    +0.14
    0.03
    231
    +0.13
    0.03
    244
    +0.13
    0.02
    Negative Logits
    "}](#
    -2.00
    PHY
    -1.42
    CLOCK
    -1.40
    OME
    -1.36
     Ages
    -1.29
     facult
    -1.29
     mind
    -1.28
    ncia
    -1.28
    documentclass
    -1.27
    zzi
    -1.27
    POSITIVE LOGITS
    1.87
           ↵
    1.87
    ↵↵
    1.87
    ↵↵↵
    1.87
    1.87
    1.87
    ↵
    1.87
    1.87
    ↵  âĢĥ
    1.87
    <|outofrange|>
    1.87
    Activations Density 0.196%

    No Known Activations