© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 2-RES-SM
    11. 12261
    Prev
    Next
    INDEX
    Explanations

    sequences indicating legal terminology or concepts, particularly in the context of jurisdiction and court proceedings

    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
    6
    +0.20
    1.2%
    263
    +0.14
    0.8%
    12
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    6
    +0.20
    0.14
    68
    +0.14
    0.10
    406
    +0.14
    0.11
    Negative Logits
    ľĵ
    -2.82
    Īĺ
    -2.67
    ŀ
    -2.44
    -2.42
    ↵↵
    -2.42
         ↵
    -2.42
    -2.42
    ↵↵
    -2.42
    -2.42
    ↵↵
    -2.42
    POSITIVE LOGITS
     possibility
    1.68
     someday
    1.47
     occasion
    1.47
     ELSE
    1.43
     exped
    1.41
    zing
    1.40
     occurrence
    1.36
     temptation
    1.33
     advis
    1.33
    }$]{}
    1.32
    Activations Density 4.072%

    No Known Activations