© 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 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. 30476
    Prev
    Next
    INDEX
    Explanations

    references to ice and related cold substances or phenomena

    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
    +0.22
    1.3%
    371
    +0.17
    1.0%
    369
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    371
    +0.22
    0.04
    56
    +0.17
    0.00
    393
    +0.12
    0.02
    Negative Logits
    inib
    -1.84
     unsuccessful
    -1.64
    inent
    -1.60
    aliana
    -1.58
    ionale
    -1.58
    adata
    -1.53
     nervous
    -1.50
     succeeding
    -1.49
     vain
    -1.49
     eager
    -1.47
    POSITIVE LOGITS
    berg
    2.13
    quist
    1.88
    breaker
    1.82
    strom
    1.78
     cream
    1.73
    balls
    1.72
    ström
    1.65
    gren
    1.61
     Ages
    1.61
     cubes
    1.58
    Activations Density 0.204%

    No Known Activations