© 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. 13868
    Prev
    Next
    INDEX
    Explanations

    phrases related to time frames and durations

    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
    202
    +0.13
    0.7%
    47
    +0.11
    0.6%
    325
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    163
    +0.13
    0.04
    477
    +0.11
    0.06
    342
    +0.11
    0.04
    Negative Logits
     secrets
    -1.75
     myself
    -1.69
     Blog
    -1.63
    blogger
    -1.58
     admin
    -1.56
     roles
    -1.49
    inely
    -1.49
     minds
    -1.48
     demons
    -1.48
    ı
    -1.45
    POSITIVE LOGITS
     elapsed
    2.21
     postoperatively
    1.81
    hold
    1.80
    [\#
    1.72
    apsed
    1.70
     intervals
    1.69
    IFY
    1.68
    enden
    1.67
    ago
    1.66
     increments
    1.66
    Activations Density 0.220%

    No Known Activations