© 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. 4-RES-SM
    11. 11346
    Prev
    Next
    INDEX
    Explanations

    mentions of villages or similar communities

    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
    +0.15
    0.8%
    279
    +0.14
    0.8%
    346
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    203
    +0.15
    0.01
    350
    +0.14
    0.02
    477
    +0.13
    0.02
    Negative Logits
     course
    -1.73
     vicinity
    -1.65
     reader
    -1.53
    dot
    -1.49
    thon
    -1.48
    ubicin
    -1.47
    izer
    -1.46
    izing
    -1.41
    unreadable
    -1.37
    ized
    -1.36
    POSITIVE LOGITS
    ½
    2.71
    ¼
    2.69
    ª
    2.68
    ij
    2.68
    Ģ
    2.62
    Ħ
    2.54
    ages
    2.54
    £
    2.51
    ©
    2.45
    ħ
    2.45
    Activations Density 0.137%

    No Known Activations