© 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. 10248
    Prev
    Next
    INDEX
    Explanations

    elements related to message handling and actions in a web application context

    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
    21
    +0.21
    1.2%
    255
    +0.18
    1.1%
    271
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    255
    +0.21
    0.01
    17
    +0.18
    0.07
    219
    +0.13
    0.09
    Negative Logits
     today
    -1.80
    rium
    -1.62
    consin
    -1.60
    endment
    -1.48
    sein
    -1.47
    shire
    -1.45
    iÄĩ
    -1.45
    soever
    -1.41
    adays
    -1.38
    anni
    -1.38
    POSITIVE LOGITS
    ı
    3.17
    ķ
    2.98
    ģ
    2.90
    µ
    2.90
    ĭ
    2.88
    ª
    2.84
    Ļ
    2.77
    ¢
    2.73
    ħ
    2.71
    ĸ
    2.68
    Activations Density 0.865%

    No Known Activations