© 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. 27860
    Prev
    Next
    INDEX
    Explanations

    specific names or identifiers, particularly related to places or entities

    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
    156
    +0.27
    1.6%
    369
    +0.26
    1.5%
    410
    +0.15
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    156
    +0.27
    0.39
    458
    +0.26
    0.37
    71
    +0.15
    0.36
    Negative Logits
    ised
    -1.76
    ights
    -1.70
    izing
    -1.68
    ising
    -1.67
    night
    -1.66
    ises
    -1.59
    ization
    -1.58
    izations
    -1.58
    izers
    -1.57
    isation
    -1.56
    POSITIVE LOGITS
    Ĵ
    4.35
    ī
    4.32
    ²
    4.09
    ³
    4.06
    «
    4.04
    ½
    4.04
    ĸ
    4.00
    IJ
    3.97
    Ĭ
    3.95
    ¦
    3.95
    Activations Density 2.048%

    No Known Activations