© 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. MLP Post
    9. 0-MLP-SM
    11. 30433
    Prev
    Next
    INDEX
    Explanations

    numerical values related to legal cases or statutes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ctigges/pythia-70m-deduped__mlp-sm_processed/0-mlp-sm
    Prompts (Dashboard)
    32,768 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.0.hook_mlp_out
    Hook Layer
    0
    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
    258
    +0.13
    0.8%
    307
    +0.12
    0.7%
    290
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    307
    +0.13
    0.05
    290
    +0.12
    0.04
    412
    +0.12
    0.03
    Negative Logits
    usterity
    -1.76
     intolerance
    -1.61
    elian
    -1.49
    olysis
    -1.46
     suspicion
    -1.46
    asting
    -1.46
     eternity
    -1.39
     steroids
    -1.38
     arrest
    -1.36
     plasma
    -1.34
    POSITIVE LOGITS
    ģ
    2.03
    ļ
    1.73
    ®
    1.71
    yards
    1.68
    º
    1.67
    Ĥ
    1.66
    sky
    1.66
     (\#
    1.64
     (§
    1.63
    pf
    1.59
    Activations Density 0.051%

    No Known Activations