© 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. 1-RES-SM
    11. 24696
    Prev
    Next
    INDEX
    Explanations

    references to experimental procedures or studies

    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/1-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.1.hook_resid_post
    Hook Layer
    1
    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
    +0.19
    1.1%
    219
    +0.11
    0.6%
    124
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    208
    +0.19
    0.01
    124
    +0.11
    0.01
    219
    +0.11
    0.01
    Negative Logits
    ruct
    -1.67
    lease
    -1.58
    roz
    -1.56
    rier
    -1.54
    ãĥ£
    -1.52
    wan
    -1.47
    lla
    -1.45
    gaard
    -1.43
    Å¡ÃŃ
    -1.43
    thon
    -1.39
    POSITIVE LOGITS
    ISM
    2.24
    izations
    2.10
    ists
    1.94
    isms
    1.92
    £
    1.88
    isations
    1.88
    itat
    1.82
    grounds
    1.79
    ¿½
    1.78
    ISTS
    1.73
    Activations Density 0.027%

    No Known Activations