© 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. 4-RES-SM
    11. 12751
    Prev
    Next
    INDEX
    Explanations

    phrases related to sexual acts and their definitions within 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/4-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.4.hook_resid_post
    Hook Layer
    4
    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
    453
    +0.14
    0.8%
    210
    +0.13
    0.7%
    47
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    47
    +0.14
    0.05
    67
    +0.13
    0.01
    289
    +0.13
    0.02
    Negative Logits
     fairness
    -1.99
     rankings
    -1.93
     ranking
    -1.84
     dividend
    -1.76
     benchmark
    -1.74
     Django
    -1.74
     HashMap
    -1.65
     Finance
    -1.61
     Yug
    -1.59
     stats
    -1.57
    POSITIVE LOGITS
     implanted
    3.15
     catheter
    3.00
    ŀ
    3.00
     implant
    2.99
     surgical
    2.96
     implants
    2.92
     surgeon
    2.88
     surgically
    2.82
    ĨĴ
    2.77
     Surgical
    2.74
    Activations Density 0.504%

    No Known Activations