© 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. 9617
    Prev
    Next
    INDEX
    Explanations

    questions about mathematical concepts or calculation requests

    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
    +0.21
    1.3%
    255
    +0.17
    1.0%
    348
    +0.16
    1.0%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    284
    +0.21
    0.01
    453
    +0.17
    0.02
    290
    +0.16
    0.01
    Negative Logits
    hift
    -1.71
    stan
    -1.49
    them
    -1.45
    rå
    -1.40
    hell
    -1.35
     them
    -1.32
     goodbye
    -1.27
    stic
    -1.26
    him
    -1.26
    ystems
    -1.26
    POSITIVE LOGITS
    ĵ
    2.06
    ¡
    2.03
    ·¸
    1.93
    º
    1.92
    ·
    1.90
    ĥ½
    1.88
     happens
    1.88
    ľĵ
    1.87
    Ļ
    1.87
    ī
    1.84
    Activations Density 0.035%

    No Known Activations