© 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. 1-RES-SM
    11. 29427
    Prev
    Next
    INDEX
    Explanations

    expressions related to the act of laying something down or placing items in a particular position

    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
    255
    +0.15
    0.8%
    325
    +0.12
    0.7%
    359
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    255
    +0.15
    0.03
    46
    +0.12
    0.02
    325
    +0.12
    0.02
    Negative Logits
     Penguin
    -1.53
    olate
    -1.50
     specific
    -1.46
     stripes
    -1.40
     controlling
    -1.39
     liking
    -1.38
    ald
    -1.38
    rh
    -1.36
     pert
    -1.32
     only
    -1.32
    POSITIVE LOGITS
    º
    2.39
    ¼
    2.00
    ¹
    1.98
    away
    1.97
    wers
    1.96
    ong
    1.92
    ´
    1.91
    ĻĤ
    1.90
    ahead
    1.90
    nesday
    1.74
    Activations Density 0.119%

    No Known Activations