© 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. 4-RES-SM
    11. 9303
    Prev
    Next
    INDEX
    Explanations

    elements related to technological or programming instructions

    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/4-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.4.hook_resid_post
    Hook Layer
    4
    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
    78
    +0.20
    1.3%
    266
    +0.13
    0.8%
    375
    +0.12
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    78
    +0.20
    0.00
    255
    +0.13
    -0.00
    126
    +0.12
    -0.00
    Negative Logits
    feas
    -1.45
    lessly
    -1.43
    mable
    -1.41
    urized
    -1.37
    ible
    -1.32
     center
    -1.32
     relativity
    -1.30
    lotte
    -1.27
     finder
    -1.25
     foreseeable
    -1.25
    POSITIVE LOGITS
    Ŀ
    2.73
    £
    2.42
    ĵ
    2.37
    §
    2.35
    Ħ
    2.32
    ¡
    2.30
    Ļ
    2.29
    IJ
    2.28
    ħ
    2.27
    ¦
    2.25
    Activations Density 0.031%

    No Known Activations