© 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. 25144
    Prev
    Next
    INDEX
    Explanations

    references to adherence to rules or standards

    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
    248
    +0.15
    0.8%
    376
    +0.12
    0.7%
    328
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    248
    +0.15
    0.02
    367
    +0.12
    0.02
    475
    +0.10
    0.01
    Negative Logits
     opportunity
    -1.52
    hire
    -1.50
    aurus
    -1.48
     spent
    -1.40
    jour
    -1.40
    stick
    -1.38
     hone
    -1.38
     episode
    -1.36
    sters
    -1.35
    apine
    -1.35
    POSITIVE LOGITS
    eps
    1.65
    emente
    1.63
    ivat
    1.59
    iya
    1.54
    alan
    1.52
    ei
    1.43
    etm
    1.41
    oplasmic
    1.41
    ©
    1.35
    lementary
    1.34
    Activations Density 0.087%

    No Known Activations