© 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. 12713
    Prev
    Next
    INDEX
    Explanations

    questions or requests for assistance

    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
    431
    +0.13
    0.7%
    87
    +0.13
    0.7%
    436
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    230
    +0.13
    0.02
    87
    +0.13
    0.02
    431
    +0.11
    0.02
    Negative Logits
    omitempty
    -1.77
    orphic
    -1.70
     each
    -1.61
    liest
    -1.57
     center
    -1.55
    ouin
    -1.53
    ocus
    -1.53
     hybridization
    -1.49
     themselves
    -1.48
     centre
    -1.43
    POSITIVE LOGITS
    where
    2.18
    İ
    2.07
    body
    1.90
    who
    1.83
    how
    1.79
    ureus
    1.74
    ī
    1.71
    Ī
    1.66
    ologies
    1.64
    Ľ
    1.63
    Activations Density 0.071%

    No Known Activations