© 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. 1-RES-SM
    11. 24242
    Prev
    Next
    INDEX
    Explanations

    advice related to maintaining one's health while traveling

    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/1-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.1.hook_resid_post
    Hook Layer
    1
    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
    23
    +0.16
    0.9%
    418
    +0.12
    0.7%
    72
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    23
    +0.16
    0.23
    478
    +0.12
    -0.02
    418
    +0.11
    0.01
    Negative Logits
    ĻĤ
    -2.55
    ¡
    -2.45
    ¿½
    -2.32
    Ī
    -2.25
    ģ
    -2.23
    »¿
    -2.20
    Ĥ¬
    -2.18
    ĨĴ
    -2.15
    į
    -2.10
    ļ
    -2.09
    POSITIVE LOGITS
     mindfulness
    1.68
    cluding
    1.58
    TRY
    1.55
     each
    1.53
     Stress
    1.46
    aging
    1.43
    cknow
    1.42
    icing
    1.40
     nitric
    1.38
     Cognitive
    1.38
    Activations Density 5.847%

    No Known Activations