© 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. 2-RES-SM
    11. 27408
    Prev
    Next
    INDEX
    Explanations

    mentions of specific days and times

    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
    358
    +0.13
    0.7%
    397
    +0.11
    0.6%
    178
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    358
    +0.13
    0.07
    287
    +0.11
    0.07
    397
    +0.11
    0.06
    Negative Logits
    Ŀ
    -2.61
    IJ
    -2.61
    ŀ
    -2.53
    ·¸
    -2.40
    ĻĤ
    -2.37
    į
    -2.30
    ĥ
    -2.29
    Ń
    -2.26
    ¿½
    -2.26
    ĵ
    -2.23
    POSITIVE LOGITS
    reon
    1.74
    lest
    1.68
    ilion
    1.66
     clocks
    1.64
    ynote
    1.58
     Vinc
    1.51
    station
    1.51
    rus
    1.50
    finder
    1.49
    ontal
    1.47
    Activations Density 0.485%

    No Known Activations