© 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. 9153
    Prev
    Next
    INDEX
    Explanations

    data related to advanced medical equipment and procedures

    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
    21
    +0.21
    1.2%
    271
    +0.14
    0.8%
    255
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    203
    +0.21
    0.02
    288
    +0.14
    0.03
    448
    +0.12
    0.02
    Negative Logits
    ément
    -1.53
    utions
    -1.46
    lessly
    -1.41
    agment
    -1.39
    ership
    -1.38
    rics
    -1.37
     %{
    -1.33
    ço
    -1.31
    icable
    -1.30
     pestic
    -1.29
    POSITIVE LOGITS
    ray
    2.21
     ray
    1.90
    rays
    1.88
    Ray
    1.73
    shaped
    1.70
    linked
    1.64
    axes
    1.56
     rays
    1.50
    axis
    1.47
    shape
    1.45
    Activations Density 0.119%

    No Known Activations