© 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 EvalsExportsAPI 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. 11495
    Prev
    Next
    INDEX
    Explanations

    references to legal cases or court rulings

    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
    255
    +0.14
    0.8%
    68
    +0.13
    0.7%
    271
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    68
    +0.14
    0.05
    424
    +0.13
    0.04
    359
    +0.12
    0.04
    Negative Logits
    eon
    -1.96
    brains
    -1.74
    eer
    -1.59
     walls
    -1.55
    ctions
    -1.52
    nement
    -1.50
    etary
    -1.48
    mentation
    -1.41
    rations
    -1.40
     order
    -1.39
    POSITIVE LOGITS
    ellers
    2.05
    vens
    2.04
    AMPLE
    2.01
    loan
    2.00
    ullivan
    2.00
    ylvania
    1.89
    chn
    1.83
    ergio
    1.83
    ensitive
    1.81
    CHO
    1.81
    Activations Density 0.066%

    No Known Activations