© 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. 29015
    Prev
    Next
    INDEX
    Explanations

    notes or references related to legal cases and decisions

    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
    +0.23
    1.3%
    491
    +0.14
    0.8%
    329
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    329
    +0.23
    0.08
    491
    +0.14
    0.07
    23
    +0.14
    0.09
    Negative Logits
     behalf
    -1.82
    bies
    -1.76
     accelerator
    -1.75
    hill
    -1.64
     herself
    -1.60
     milieu
    -1.58
    econom
    -1.56
    icago
    -1.55
     economy
    -1.54
    googleapis
    -1.53
    POSITIVE LOGITS
    ittings
    1.93
    rangle
    1.64
    PECT
    1.56
    cludes
    1.52
     0000000000000000000000000000000000
    1.51
    ãģª
    1.47
    verted
    1.47
    documentclass
    1.46
     except
    1.43
    uff
    1.43
    Activations Density 2.089%

    No Known Activations