© 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. 26814
    Prev
    Next
    INDEX
    Explanations

    references to consumption and usage metrics in various contexts

    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
    156
    +0.14
    0.8%
    247
    +0.13
    0.7%
    186
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    186
    +0.14
    0.02
    335
    +0.13
    0.03
    247
    +0.12
    0.03
    Negative Logits
    ¿½
    -1.78
    umat
    -1.76
    yx
    -1.73
    ĻĤ
    -1.73
    ķ
    -1.69
    ±
    -1.63
    amais
    -1.62
    pei
    -1.60
    rept
    -1.50
     tears
    -1.50
    POSITIVE LOGITS
    zione
    1.85
     amounts
    1.77
     amount
    1.73
     habits
    1.70
     rate
    1.68
     variance
    1.67
     lasts
    1.66
     dates
    1.66
     accru
    1.66
    criptor
    1.66
    Activations Density 0.241%

    No Known Activations