© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. Residuals
    5. 2-RES-SM
    6. 11124
    Prev
    Next
    INDEX
    Explanations

    structured data snippets or code-like segments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ctigges/pythia-70m-deduped__res-sm_processed/2-res-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_resid_post
    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
    244
    +0.15
    0.9%
    330
    +0.14
    0.8%
    381
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    381
    +0.15
    0.15
    244
    +0.14
    0.14
    330
    +0.14
    0.09
    Negative Logits
     ahead
    -1.39
    ulating
    -1.37
     Marty
    -1.32
    asters
    -1.32
     Superman
    -1.32
     seasons
    -1.31
     Snyder
    -1.29
     Lieutenant
    -1.29
    iles
    -1.28
     selenium
    -1.24
    POSITIVE LOGITS
    lickr
    2.08
    º
    1.77
    »
    1.72
    »¿
    1.70
    ¶
    1.67
    anca
    1.66
    ĨĴ
    1.49
    ¹
    1.49
    Ļ
    1.47
    ³
    1.43
    Activations Density 6.053%

    No Known Activations