© 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. 13870
    Prev
    Next
    INDEX
    Explanations

    information related to technology and product specifications

    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
    156
    +0.23
    1.3%
    25
    +0.16
    0.9%
    73
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    73
    +0.23
    0.11
    83
    +0.16
    0.08
    298
    +0.12
    0.05
    Negative Logits
    ©
    -5.11
    ŀ
    -4.82
    ĵ
    -4.67
    ĻĤ
    -4.55
    ¯
    -4.50
    -4.47
    č↵
    -4.47
    -4.47
    ↵
    -4.47
    ↵
    -4.47
    POSITIVE LOGITS
    ccess
    1.80
    iginally
    1.68
     Fargo
    1.56
    addle
    1.51
    astolic
    1.46
    htra
    1.44
    ting
    1.43
    abeth
    1.42
    stract
    1.41
    ÅĽci
    1.40
    Activations Density 1.502%

    No Known Activations