© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 10963
    Prev
    Next
    INDEX
    Explanations

    concepts related to fitness and exercise benefits

    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
    426
    +0.15
    0.8%
    150
    +0.14
    0.8%
    234
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    426
    +0.15
    0.14
    154
    +0.14
    0.13
    307
    +0.11
    0.06
    Negative Logits
    »
    -2.05
    ¶
    -2.03
    µ
    -1.99
    ¹
    -1.93
    ¾
    -1.91
    ©
    -1.90
    ²
    -1.84
    ¨
    -1.84
    ½
    -1.75
    £
    -1.74
    POSITIVE LOGITS
     Against
    1.81
     Arms
    1.79
     Abuse
    1.72
     Studies
    1.71
     Age
    1.68
     Experience
    1.67
     Lives
    1.66
     Recovery
    1.66
     Achie
    1.66
     Mem
    1.65
    Activations Density 2.556%

    No Known Activations