© 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. 28446
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing the concept of importance

    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
    365
    +0.13
    0.7%
    376
    +0.12
    0.7%
    72
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    216
    +0.13
    0.02
    72
    +0.12
    0.02
    365
    +0.11
    0.01
    Negative Logits
    neys
    -1.97
    gie
    -1.73
    rives
    -1.71
    ++
    -1.70
    derer
    -1.64
    cker
    -1.61
    chen
    -1.57
    anie
    -1.55
    mighty
    -1.53
    wed
    -1.52
    POSITIVE LOGITS
    ŀ
    1.89
    ·
    1.82
    arily
    1.81
    ¨
    1.78
    ĸ
    1.78
    ł
    1.75
    Ķ
    1.73
    ģ
    1.72
    ¢
    1.65
    ously
    1.65
    Activations Density 0.060%

    No Known Activations