© 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. 28272
    Prev
    Next
    INDEX
    Explanations

    expressions of necessity or urgency

    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
    314
    +0.12
    0.6%
    5
    +0.12
    0.6%
    376
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    344
    +0.12
    0.04
    435
    +0.12
    0.04
    501
    +0.11
    0.03
    Negative Logits
    à±ģ
    -2.23
    à°¿
    -1.84
    à±
    -1.81
    unnumbered
    -1.67
    à±į
    -1.67
    ி
    -1.60
    à¯ģ
    -1.58
    osp
    -1.55
    falls
    -1.54
    orea
    -1.52
    POSITIVE LOGITS
    lessly
    2.15
    ingly
    1.94
     remedy
    1.70
    ocratic
    1.69
    y
    1.62
    leman
    1.62
    aid
    1.55
     probe
    1.53
    icular
    1.50
    less
    1.48
    Activations Density 0.091%

    No Known Activations