© 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. 2-RES-SM
    11. 29637
    Prev
    Next
    INDEX
    Explanations

    phrases that include the preposition "of"

    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/2-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.2.hook_resid_post
    Hook Layer
    2
    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
    478
    +0.15
    0.8%
    159
    +0.12
    0.7%
    98
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    404
    +0.15
    0.04
    457
    +0.12
    0.03
    81
    +0.11
    0.03
    Negative Logits
     perspective
    -1.49
    iscus
    -1.45
    js
    -1.42
     surroundings
    -1.42
    ring
    -1.41
    yards
    -1.41
     dimensions
    -1.38
     footsteps
    -1.38
     properties
    -1.38
     compartments
    -1.37
    POSITIVE LOGITS
    ľĵ
    1.73
    MOESM
    1.66
    ĥ½
    1.65
    Ń
    1.62
    rese
    1.51
    said
    1.49
     Fig
    1.48
    ---|---|---
    1.47
    anco
    1.41
    ↵
    1.41
    Activations Density 0.153%

    No Known Activations