© 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. 29218
    Prev
    Next
    INDEX
    Explanations

    references to rules, laws, and language-related structures

    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
    +0.15
    0.8%
    450
    +0.11
    0.6%
    184
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    184
    +0.15
    0.13
    365
    +0.11
    0.10
    287
    +0.11
    0.11
    Negative Logits
    »¿
    -1.88
    KES
    -1.87
    ATES
    -1.82
    §
    -1.81
    ishes
    -1.80
    cludes
    -1.79
    visiae
    -1.78
    ---|---|---
    -1.76
    MENTS
    -1.73
    verts
    -1.69
    POSITIVE LOGITS
    creen
    2.09
    ource
    1.90
    heet
    1.78
    pace
    1.77
    ume
    1.73
    helf
    1.70
    cript
    1.69
    ieve
    1.66
    mith
    1.62
    ensor
    1.61
    Activations Density 1.334%

    No Known Activations