© 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. 25572
    Prev
    Next
    INDEX
    Explanations

    terms related to implied conditions and limitations in legal contexts

    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
    47
    +0.12
    0.7%
    376
    +0.11
    0.7%
    252
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    509
    +0.12
    0.02
    252
    +0.11
    0.01
    493
    +0.11
    0.01
    Negative Logits
     day
    -1.84
    ´
    -1.67
     morning
    -1.66
    ł
    -1.61
    »
    -1.61
    ¿
    -1.61
    ĥ
    -1.59
    ĺ
    -1.56
    ħ
    -1.55
    hthal
    -1.52
    POSITIVE LOGITS
     warranty
    1.92
    itud
    1.72
    ario
    1.61
     trademarks
    1.55
     betting
    1.51
    uable
    1.51
    aggio
    1.46
     residing
    1.44
     estoppel
    1.40
     gambling
    1.39
    Activations Density 0.043%

    No Known Activations