© 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. 1-RES-SM
    11. 25869
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions, calculations, and data-related content

    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/1-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.1.hook_resid_post
    Hook Layer
    1
    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
    93
    +0.17
    0.9%
    497
    +0.13
    0.7%
    121
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    17
    +0.17
    0.02
    136
    +0.13
    -0.02
    425
    +0.13
    0.05
    Negative Logits
     California
    -1.67
     Defendants
    -1.53
    atically
    -1.47
    ?’
    -1.42
     Arizona
    -1.38
     '</
    -1.32
    kin
    -1.31
     \(
    -1.31
     Records
    -1.31
    .’”
    -1.30
    POSITIVE LOGITS
    ·¸
    2.53
    ĥ½
    2.32
    ±
    2.15
    ¹
    2.05
    »
    2.02
    Ĵ
    2.00
    ³
    1.99
    ¬
    1.91
    Ŀ
    1.87
    ¢
    1.87
    Activations Density 1.019%

    No Known Activations