© 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
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. Residuals
    5. 2-RES-SM
    6. 31742
    Prev
    Next
    INDEX
    Explanations

    references to time, particularly phrases indicating a future point or subsequent events

    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
    266
    +0.14
    0.8%
    15
    +0.13
    0.7%
    502
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    266
    +0.14
    0.03
    15
    +0.13
    0.04
    91
    +0.12
    0.03
    Negative Logits
    ĻĤ
    -3.22
    »¿
    -2.89
    ĩ
    -2.77
    ĸ
    -2.71
    ³
    -2.67
    Į
    -2.66
    Ļª
    -2.65
    ¹
    -2.52
    ·¸
    -2.47
    º
    -2.41
    POSITIVE LOGITS
    ality
    2.02
     iterations
    1.90
     generations
    1.80
    than
    1.79
     than
    1.70
    noon
    1.69
     years
    1.57
     Than
    1.56
    ioned
    1.52
     renamed
    1.51
    Activations Density 0.083%

    No Known Activations