© 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. 9708
    Prev
    Next
    INDEX
    Explanations

    numerical data and statistics

    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
    +0.19
    1.1%
    78
    +0.16
    0.9%
    348
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    502
    +0.19
    0.08
    477
    +0.16
    0.07
    350
    +0.11
    0.05
    Negative Logits
     history
    -1.70
     establishment
    -1.56
     literature
    -1.51
     neutrality
    -1.48
     abroad
    -1.45
    ]{.
    -1.45
     theory
    -1.45
    hoe
    -1.43
    experience
    -1.41
     ourselves
    -1.40
    POSITIVE LOGITS
    Ĵ
    1.73
    Ľ
    1.73
    Ļª
    1.72
    6789
    1.64
    14514500
    1.58
    áĢº
    1.57
    ERTYPE
    1.57
    ANNEL
    1.55
    ktop
    1.55
    OOGLE
    1.53
    Activations Density 0.578%

    No Known Activations