© 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. 24857
    Prev
    Next
    INDEX
    Explanations

    legal terms and references within legal documents

    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
    180
    +0.11
    0.6%
    194
    +0.11
    0.6%
    263
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    54
    +0.11
    0.03
    258
    +0.11
    0.02
    425
    +0.11
    0.02
    Negative Logits
    ishing
    -1.75
     echo
    -1.67
    cluding
    -1.57
    atching
    -1.53
    ```
    -1.52
    awning
    -1.50
    EOF
    -1.48
    acent
    -1.48
    forming
    -1.48
    inkling
    -1.47
    POSITIVE LOGITS
    »¿
    2.15
    º
    2.00
    ľ
    1.75
    Ń
    1.70
    ®
    1.69
    ¸
    1.66
    Ģ
    1.64
    ĩ
    1.62
    ł
    1.62
    ĺ
    1.60
    Activations Density 0.330%

    No Known Activations