© 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. 12380
    Prev
    Next
    INDEX
    Explanations

    terms related to legal proceedings or court cases

    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
    263
    +0.15
    0.9%
    156
    +0.15
    0.8%
    354
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    150
    +0.15
    0.08
    362
    +0.15
    0.08
    56
    +0.13
    -0.04
    Negative Logits
    ĥ½
    -2.01
     genome
    -1.84
     malignancy
    -1.77
     cosmology
    -1.72
     dictionary
    -1.67
     ontology
    -1.64
    hatic
    -1.64
     genomic
    -1.63
     secrets
    -1.63
     completeness
    -1.62
    POSITIVE LOGITS
    motor
    2.40
     cars
    2.17
    wheel
    2.15
     trucks
    2.07
     motors
    2.06
     automobile
    2.06
     passengers
    2.04
    Rail
    2.03
    cars
    2.02
     Honda
    1.98
    Activations Density 2.422%

    No Known Activations