© 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. 29660
    Prev
    Next
    INDEX
    Explanations

    articles in a text

    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
    98
    +0.17
    1.0%
    326
    +0.14
    0.8%
    23
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    171
    +0.17
    0.03
    123
    +0.14
    0.06
    466
    +0.14
    0.05
    Negative Logits
    ictions
    -1.99
     notes
    -1.72
    liness
    -1.70
     prices
    -1.68
    ÃŃas
    -1.67
    enance
    -1.66
    aciones
    -1.57
    abad
    -1.54
     tables
    -1.53
    endas
    -1.53
    POSITIVE LOGITS
    ĸ
    2.71
    Ĵ
    2.67
    Ŀ
    2.39
    ĸ´
    2.21
    ľ
    2.16
    ´
    2.16
    °
    2.15
    ĵ
    2.12
    ĥ
    2.12
    Ĥ
    2.09
    Activations Density 0.286%

    No Known Activations