© 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. 12411
    Prev
    Next
    INDEX
    Explanations

    references to specific actions or statuses related to contracts and legal documents

    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
    29
    +0.17
    1.0%
    156
    +0.16
    0.9%
    162
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    29
    +0.17
    0.05
    148
    +0.16
    0.03
    162
    +0.14
    0.08
    Negative Logits
    lessly
    -1.73
    fully
    -1.67
    clusively
    -1.55
    pired
    -1.52
    stood
    -1.50
    fered
    -1.45
     guaranteed
    -1.40
     manifested
    -1.38
    ally
    -1.37
    ked
    -1.37
    POSITIVE LOGITS
    ĻĤ
    4.90
    ¾
    4.22
    ³
    4.04
    ¸
    3.90
    3.86
    3.86
    <|outofrange|>
    3.86
    ↵
    3.86
    č↵
    3.86
    3.86
    Activations Density 0.832%

    No Known Activations