© 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. 10020
    Prev
    Next
    INDEX
    Explanations

    the presence of the word "om"

    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
    391
    +0.16
    0.9%
    18
    +0.12
    0.7%
    59
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    391
    +0.16
    0.03
    399
    +0.12
    0.02
    18
    +0.12
    0.02
    Negative Logits
    MSO
    -1.82
     existence
    -1.57
    ESULT
    -1.50
    existence
    -1.50
    semin
    -1.47
    SUCCESS
    -1.46
     latter
    -1.43
     affirmative
    -1.42
     contrary
    -1.39
     *"
    -1.39
    POSITIVE LOGITS
    ī
    2.18
    berg
    2.06
    phy
    2.04
    ni
    1.89
    atsu
    1.88
    ¾
    1.87
    ģ
    1.87
    ĨĴ
    1.84
    ¹
    1.82
    ission
    1.81
    Activations Density 0.115%

    No Known Activations