© 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. 9663
    Prev
    Next
    INDEX
    Explanations

    medical and statistical data related to health metrics

    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
    63
    +0.11
    0.6%
    337
    +0.11
    0.6%
    153
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.11
    0.35
    156
    +0.11
    0.34
    71
    +0.11
    0.31
    Negative Logits
    ĻĤ
    -2.81
    ½
    -2.49
    ³
    -2.47
    ©
    -2.32
    ·¸
    -2.28
    ħ
    -2.22
    ĸ´
    -2.13
    -2.13
    ↵↵
    -2.13
    ↵
    -2.13
    POSITIVE LOGITS
     inversely
    1.88
     normalized
    1.77
     rate
    1.74
     constant
    1.72
     exponent
    1.72
     coe
    1.72
     constants
    1.71
    icity
    1.70
     predictor
    1.70
    imum
    1.70
    Activations Density 3.097%

    No Known Activations