© 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. 25450
    Prev
    Next
    INDEX
    Explanations

    the occurrence of the word "notify" 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/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
    +0.21
    1.2%
    156
    +0.16
    0.9%
    407
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    56
    +0.21
    0.00
    147
    +0.16
    0.02
    290
    +0.14
    0.02
    Negative Logits
    ]>
    -1.66
    hey
    -1.65
     compete
    -1.55
     collaborate
    -1.52
    hire
    -1.48
     discuss
    -1.48
    OCK
    -1.40
     say
    -1.33
    Kin
    -1.33
    >()
    -1.32
    POSITIVE LOGITS
    ¡
    2.36
    ®
    2.35
    ¥
    2.33
    ¢
    2.27
    ģ
    2.26
    ¯
    2.23
    Ń
    2.21
    ¨
    2.16
    ª
    2.09
    Ħ
    2.09
    Activations Density 7.702%

    No Known Activations