© 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. 14283
    Prev
    Next
    INDEX
    Explanations

    configuration commands and package management operations in scripts

    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
    307
    +0.39
    2.4%
    466
    +0.18
    1.1%
    350
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    17
    +0.39
    0.07
    261
    +0.18
    0.06
    350
    +0.13
    0.08
    Negative Logits
     Athletics
    -1.64
     athletes
    -1.53
    oelectric
    -1.46
    lying
    -1.36
     CURIAM
    -1.34
    bands
    -1.34
    band
    -1.31
     matters
    -1.30
    ickness
    -1.27
     Airlines
    -1.27
    POSITIVE LOGITS
    ¼
    3.27
    ĭ
    3.19
    ½
    3.18
    ĻĤ
    3.17
    ĨĴ
    3.10
    Ļª
    3.09
    ¹
    3.04
    ľĵ
    3.03
    ŀ
    3.00
    Ĩ
    2.99
    Activations Density 1.130%

    No Known Activations