© 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. 25436
    Prev
    Next
    INDEX
    Explanations

    references to time intervals

    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
    +0.17
    0.9%
    376
    +0.13
    0.7%
    413
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.17
    0.08
    156
    +0.13
    0.05
    271
    +0.11
    0.03
    Negative Logits
    igate
    -1.72
    appropri
    -1.64
    iquity
    -1.64
    ylan
    -1.55
     innocence
    -1.55
    beans
    -1.45
    rugged
    -1.40
     fortune
    -1.38
    ½
    -1.33
     contempt
    -1.32
    POSITIVE LOGITS
     interval
    1.82
     intervals
    1.82
    ional
    1.68
    zan
    1.66
    ichlet
    1.65
    ilinear
    1.63
    zt
    1.59
    ago
    1.59
    borne
    1.57
    Interval
    1.52
    Activations Density 0.306%

    No Known Activations