© 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. 1-RES-SM
    11. 28596
    Prev
    Next
    INDEX
    Explanations

    references to legal or judicial terms and case citations

    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
    369
    +0.21
    1.2%
    59
    +0.17
    0.9%
    502
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    59
    +0.21
    0.02
    502
    +0.17
    0.02
    120
    +0.14
    0.01
    Negative Logits
    ĸ´
    -4.18
    ľĵ
    -4.03
    ĥ½
    -4.01
    »¿
    -3.69
    Ĥ¬
    -3.60
    Īĺ
    -3.48
    ¼
    -3.45
    ĥ
    -3.43
    ĺ
    -3.38
    Ŀ
    -3.36
    POSITIVE LOGITS
    ygon
    2.24
    aris
    1.81
    lon
    1.73
    ynom
    1.64
     reached
    1.63
    isans
    1.60
    isan
    1.59
    ley
    1.59
     (@
    1.58
    ÃŃs
    1.58
    Activations Density 0.048%

    No Known Activations