© 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. 30896
    Prev
    Next
    INDEX
    Explanations

    Java class declarations and their modifiers

    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
    410
    +0.17
    1.0%
    407
    +0.14
    0.8%
    499
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    410
    +0.17
    0.06
    360
    +0.14
    0.03
    312
    +0.13
    0.04
    Negative Logits
    .]{}
    -1.72
    ]{.
    -1.59
    ]{}.
    -1.54
     \[[
    -1.53
    .](
    -1.53
    .]
    -1.52
     deposited
    -1.50
     ]{}
    -1.48
     Credit
    -1.47
     opt
    -1.41
    POSITIVE LOGITS
    ĻĤ
    1.91
    ¾
    1.56
    constructor
    1.54
    ↵
    1.52
    1.52
    ↵
    1.52
     ↵
    1.52
    č↵
    1.52
    ↵
    1.52
    ↵
    1.52
    Activations Density 0.292%

    No Known Activations