© 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 EvalsExportsAPI 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. 10658
    Prev
    Next
    INDEX
    Explanations

    specific names or identifiers associated with events or entities

    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
    +0.33
    2.0%
    369
    +0.23
    1.4%
    410
    +0.20
    1.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    410
    +0.33
    0.13
    369
    +0.23
    0.07
    129
    +0.20
    -0.00
    Negative Logits
    ropol
    -1.66
    actic
    -1.43
     [-
    -1.37
    bial
    -1.26
    *;
    -1.25
    ↵
    -1.25
    uper
    -1.24
     monkeys
    -1.24
     cult
    -1.23
    atorial
    -1.22
    POSITIVE LOGITS
    Į
    2.89
    »¿
    2.67
    Ļª
    2.59
    ¿
    2.59
    ·¸
    2.55
    ½
    2.54
    ±
    2.44
    ¬
    2.43
    ¡
    2.42
    ¾
    2.39
    Activations Density 0.792%

    No Known Activations