© 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. 10300
    Prev
    Next
    INDEX
    Explanations

    numerical values and units of measurement

    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
    +0.35
    2.2%
    156
    +0.23
    1.5%
    337
    +0.22
    1.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    21
    +0.35
    0.03
    337
    +0.23
    0.10
    186
    +0.22
    0.07
    Negative Logits
    ↵
    -5.72
    <|outofrange|>
    -5.72
    -5.72
    <|outofrange|>
    -5.72
     ↵
    -5.72
    <|outofrange|>
    -5.72
    -5.72
    -5.72
     ↵
    -5.72
    ↵
    -5.72
    POSITIVE LOGITS
     but
    1.77
    but
    1.59
     than
    1.50
     although
    1.42
    ,^[@
    1.40
     lacks
    1.40
     though
    1.39
     whereas
    1.39
     except
    1.36
     meets
    1.32
    Activations Density 3.330%

    No Known Activations