© 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. 2-RES-SM
    11. 30874
    Prev
    Next
    INDEX
    Explanations

    references to legal processes and judicial decisions

    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/2-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.2.hook_resid_post
    Hook Layer
    2
    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
    156
    +0.19
    1.0%
    246
    +0.11
    0.6%
    508
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    33
    +0.19
    0.23
    430
    +0.11
    0.13
    492
    +0.11
    0.14
    Negative Logits
    IZE
    -1.53
     Foods
    -1.48
    meter
    -1.48
    ered
    -1.40
     charts
    -1.36
    =”
    -1.36
    rone
    -1.35
    burg
    -1.33
     cookies
    -1.31
     Rhe
    -1.31
    POSITIVE LOGITS
     forthcoming
    1.59
    blockList
    1.54
     deserves
    1.51
     deserved
    1.51
     respective
    1.50
     exception
    1.49
    >();
    1.49
    ();
    1.47
    ![**
    1.47
     result
    1.44
    Activations Density 10.159%

    No Known Activations