© 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. 12677
    Prev
    Next
    INDEX
    Explanations

    information related to real-time data and monitoring systems

    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
    302
    +0.15
    0.8%
    391
    +0.12
    0.7%
    246
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    391
    +0.15
    0.03
    68
    +0.12
    0.03
    302
    +0.12
    0.03
    Negative Logits
    ocene
    -1.76
     heavier
    -1.65
    ffen
    -1.61
     accomplished
    -1.60
     erected
    -1.56
    arum
    -1.54
    ]'
    -1.51
    aceae
    -1.47
     immig
    -1.46
    acre
    -1.45
    POSITIVE LOGITS
    ĨĴ
    2.48
    ĩ
    2.42
    Ĺ
    2.40
    ľ
    2.40
    £
    2.30
    Ļ
    2.19
    Ł
    2.12
    ĵ
    2.10
    ĻĤ
    2.09
    ¡
    2.04
    Activations Density 0.447%

    No Known Activations