© 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. 13934
    Prev
    Next
    INDEX
    Explanations

    references to personal views, opinions, and discussions related to various topics

    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
    306
    +0.15
    0.9%
    488
    +0.13
    0.7%
    66
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    401
    +0.15
    0.06
    66
    +0.13
    0.07
    511
    +0.12
    0.10
    Negative Logits
    ¥
    -6.31
    Ł
    -6.21
    ı
    -6.17
    -6.04
     ↵
    -6.04
    č↵
    -6.04
    ↵↵
    -6.04
           ↵
    -6.04
    ↵
    -6.04
    -6.04
    POSITIVE LOGITS
    heet
    3.24
    creen
    3.10
     about
    3.07
    heets
    2.84
     regarding
    2.80
     concerning
    2.63
    ync
    2.46
    ynaptic
    2.45
    pecific
    2.34
    mith
    2.31
    Activations Density 1.114%

    No Known Activations