© 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. 9968
    Prev
    Next
    INDEX
    Explanations

    references to programming languages, particularly Java

    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
    +0.14
    0.8%
    271
    +0.13
    0.7%
    292
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    204
    +0.14
    0.03
    55
    +0.13
    0.03
    454
    +0.12
    0.02
    Negative Logits
     cancell
    -1.68
    rile
    -1.63
     consequence
    -1.57
    lando
    -1.57
     goodbye
    -1.56
    chers
    -1.54
    akers
    -1.52
    lessness
    -1.48
    ching
    -1.45
    cted
    -1.44
    POSITIVE LOGITS
    £
    3.55
    Ļª
    3.44
    ĨĴ
    3.40
    ¶
    3.29
    ĻĤ
    3.23
    ³
    3.22
    ¹
    3.22
    ©
    3.17
    ĺ
    3.14
    ¡
    3.04
    Activations Density 0.057%

    No Known Activations