© 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. 28839
    Prev
    Next
    INDEX
    Explanations

    instances of the word "retreat."

    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
    115
    +0.17
    1.0%
    450
    +0.13
    0.7%
    59
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    400
    +0.17
    0.01
    339
    +0.13
    0.01
    59
    +0.12
    0.01
    Negative Logits
     sweat
    -1.91
    oxide
    -1.51
     Wales
    -1.50
     Scotland
    -1.48
     Commonwealth
    -1.46
     immensely
    -1.39
     immigration
    -1.36
    reland
    -1.34
    uka
    -1.28
    hin
    -1.27
    POSITIVE LOGITS
    µ
    2.02
    ł
    1.97
    ¨
    1.97
    £
    1.97
    ¡
    1.95
    ·¸
    1.92
    °
    1.85
    ing
    1.85
    ¶
    1.85
    Ł
    1.85
    Activations Density 0.031%

    No Known Activations