© 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. 30561
    Prev
    Next
    INDEX
    Explanations

    actions and processes related to evaluation and assessment

    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
    23
    +0.18
    1.0%
    376
    +0.14
    0.8%
    68
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    317
    +0.18
    0.09
    376
    +0.14
    0.03
    23
    +0.12
    0.10
    Negative Logits
    shire
    -1.98
    sburg
    -1.72
    teenth
    -1.69
     meets
    -1.65
    ska
    -1.65
    plings
    -1.63
    's
    -1.60
     responds
    -1.59
    į
    -1.58
    vist
    -1.55
    POSITIVE LOGITS
    hift
    1.93
    urface
    1.61
    creen
    1.61
    ôle
    1.60
    chitz
    1.57
    ize
    1.48
    ymbol
    1.46
    ickness
    1.44
    aturation
    1.42
    afe
    1.42
    Activations Density 0.922%

    No Known Activations