© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. Residuals
    9. 4-RES-SM
    11. 13126
    Prev
    Next
    INDEX
    Explanations

    numerical data related to statistics and measurements

    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/4-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.4.hook_resid_post
    Hook Layer
    4
    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
    +0.26
    1.6%
    36
    +0.18
    1.1%
    280
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    36
    +0.26
    0.05
    280
    +0.18
    0.01
    313
    +0.13
    0.02
    Negative Logits
     Register
    -1.59
     dropdown
    -1.59
     Release
    -1.57
     Firm
    -1.51
     Variables
    -1.50
     Name
    -1.48
     generality
    -1.48
     variables
    -1.47
     Title
    -1.46
     Comments
    -1.41
    POSITIVE LOGITS
    later
    2.00
    and
    1.98
    whose
    1.97
    Ĭ
    1.96
    that
    1.95
    with
    1.91
    founded
    1.91
    IJ
    1.89
    during
    1.88
    which
    1.86
    Activations Density 0.167%

    No Known Activations