© 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. 26344
    Prev
    Next
    INDEX
    Explanations

    specific structural or technical elements in academic or scientific texts

    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
    23
    +0.18
    1.1%
    238
    +0.13
    0.8%
    169
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    53
    +0.18
    0.05
    438
    +0.13
    0.04
    189
    +0.12
    0.02
    Negative Logits
     indic
    -1.56
     cerevisiae
    -1.51
     itself
    -1.49
     likes
    -1.46
     dice
    -1.46
     reserve
    -1.45
    illon
    -1.45
     (“
    -1.44
    timer
    -1.43
    ismatic
    -1.42
    POSITIVE LOGITS
    ====================
    1.61
    ----------------------------------
    1.59
    ==========
    1.58
    à±
    1.57
    ---------------------------------
    1.54
    -----------------------------------
    1.47
    APS
    1.46
    ALSE
    1.43
    ATIONS
    1.42
    --------------------------------
    1.42
    Activations Density 0.342%

    No Known Activations