© 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. 26471
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to structured educational frameworks and standards

    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
    394
    +0.14
    0.8%
    77
    +0.14
    0.8%
    290
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    77
    +0.14
    0.03
    111
    +0.14
    0.03
    70
    +0.11
    0.02
    Negative Logits
    noreply
    -1.58
    voice
    -1.50
     questions
    -1.39
    cluding
    -1.38
    quiry
    -1.36
    osing
    -1.36
    drew
    -1.36
    other
    -1.34
    debted
    -1.32
     laughter
    -1.32
    POSITIVE LOGITS
    §
    3.79
    ľ
    3.70
    ģ
    3.56
    Ļ
    3.35
    Ĵ
    3.27
    Ŀ
    3.26
    ©
    3.17
    ĸ´
    3.07
    ĨĴ
    3.07
    ª
    3.06
    Activations Density 0.043%

    No Known Activations