© 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. 25721
    Prev
    Next
    INDEX
    Explanations

    the word "such" and its variations in context

    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
    118
    +0.15
    0.8%
    39
    +0.14
    0.8%
    402
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    39
    +0.15
    0.09
    118
    +0.14
    0.08
    432
    +0.11
    0.07
    Negative Logits
    áĥĶáĥ
    -1.63
    't
    -1.57
     bool
    -1.55
    áĥĶ
    -1.42
     clue
    -1.37
     honestly
    -1.34
    áĥĺ
    -1.31
     Titan
    -1.30
    Prefab
    -1.29
    boolean
    -1.29
    POSITIVE LOGITS
    ĥ½
    2.48
    ĨĴ
    1.89
     ↵
    1.75
    <|outofrange|>
    1.75
    č↵č↵
    1.75
    ↵
    1.75
    ↵↵↵
    1.75
    ↵↵
    1.75
    <|outofrange|>
    1.75
    1.75
    Activations Density 4.443%

    No Known Activations