© 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. 28381
    Prev
    Next
    INDEX
    Explanations

    specific legal terminology and references related to court proceedings

    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
    122
    +0.17
    0.9%
    127
    +0.15
    0.8%
    98
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    122
    +0.17
    0.09
    127
    +0.15
    0.16
    138
    +0.11
    0.10
    Negative Logits
    ľĵ
    -4.02
     ↵
    -3.67
    ↵
    -3.67
    ↵
    -3.67
    <|outofrange|>
    -3.67
              ↵
    -3.67
    ↵
    -3.67
    -3.67
    ↵↵
    -3.67
    ↵
    -3.67
    POSITIVE LOGITS
    quot
    1.31
     Field
    1.29
     forecast
    1.29
    KA
    1.25
    ployment
    1.25
    KY
    1.23
    aming
    1.23
     Armed
    1.20
    amar
    1.20
     Operation
    1.18
    Activations Density 3.719%

    No Known Activations