© 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. Residuals
    9. 2-RES-SM
    11. 26496
    Prev
    Next
    INDEX
    Explanations

    technical terms and references related to data management and system functions

    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
    156
    +0.23
    1.4%
    261
    +0.18
    1.1%
    369
    +0.18
    1.1%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    261
    +0.23
    0.08
    50
    +0.18
    0.06
    497
    +0.18
    0.03
    Negative Logits
    assium
    -1.45
    opolys
    -1.44
    icable
    -1.39
    Willi
    -1.35
     delim
    -1.34
     syll
    -1.33
     boundaries
    -1.31
     deriving
    -1.31
     hypothesis
    -1.30
     pronounce
    -1.25
    POSITIVE LOGITS
    ĸ
    3.99
    Ļª
    3.96
    ĨĴ
    3.92
    ı
    3.90
    3.85
    ↵
    3.85
    <|outofrange|>
    3.85
    3.85
    3.85
    č↵
    3.85
    Activations Density 4.150%

    No Known Activations