© 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. 2-RES-SM
    11. 10579
    Prev
    Next
    INDEX
    Explanations

    patterns related to legal terminology and concepts

    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
    287
    +0.15
    0.8%
    240
    +0.14
    0.8%
    48
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    287
    +0.15
    0.12
    361
    +0.14
    0.08
    369
    +0.13
    0.02
    Negative Logits
    ¹
    -1.69
    ¿
    -1.62
    ı
    -1.56
    ”.
    -1.52
    IJ
    -1.48
    ray
    -1.43
    Ļª
    -1.41
    ¬
    -1.40
    lite
    -1.38
    °
    -1.36
    POSITIVE LOGITS
    FPar
    1.59
     omission
    1.48
     hypothesis
    1.46
     reason
    1.44
     assumption
    1.44
    breviations
    1.42
    theless
    1.39
     respondent
    1.35
    sson
    1.34
    judgment
    1.33
    Activations Density 2.644%

    No Known Activations