© 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. 25535
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to translation services

    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
    156
    +0.12
    0.7%
    143
    +0.11
    0.6%
    500
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    143
    +0.12
    0.02
    500
    +0.11
    0.02
    230
    +0.10
    0.02
    Negative Logits
     sacrifice
    -1.48
    coat
    -1.45
    opause
    -1.45
     absence
    -1.45
    haviour
    -1.44
    ev
    -1.44
     equivalently
    -1.42
    iji
    -1.40
    brook
    -1.39
    ubation
    -1.38
    POSITIVE LOGITS
    mith
    1.60
    smen
    1.53
    ophone
    1.52
    liter
    1.51
    roup
    1.48
    fiddle
    1.48
    genic
    1.44
    ricular
    1.41
    namese
    1.38
    ized
    1.38
    Activations Density 0.092%

    No Known Activations