© 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. 1-RES-SM
    11. 26243
    Prev
    Next
    INDEX
    Explanations

    terms related to scientific processes and classifications

    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/1-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.1.hook_resid_post
    Hook Layer
    1
    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
    131
    +0.11
    0.6%
    417
    +0.10
    0.6%
    383
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    417
    +0.11
    0.01
    109
    +0.10
    0.00
    331
    +0.10
    0.01
    Negative Logits
    Ļª
    -3.59
    »¿
    -3.50
    »
    -3.28
    ½
    -3.18
    ĺ
    -3.15
    ĥ½
    -3.12
    Ŀ
    -3.09
    Ĩ
    -3.02
    ĭ
    -3.02
    ľĵ
    -3.00
    POSITIVE LOGITS
    ists
    1.77
    ist
    1.66
    ism
    1.51
    isms
    1.43
    ologist
    1.41
    istes
    1.39
    smith
    1.36
    work
    1.35
     Hearing
    1.33
     footsteps
    1.31
    Activations Density 0.139%

    No Known Activations