© 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
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. Residuals
    5. 4-RES-SM
    6. 11996
    Prev
    Next
    INDEX
    Explanations

    terms related to personal ownership and entities

    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
    156
    +0.55
    4.4%
    111
    +0.52
    4.2%
    510
    +0.09
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    156
    +0.55
    0.41
    205
    +0.52
    0.48
    40
    +0.09
    0.46
    Negative Logits
    ĥ½
    -3.60
    ¦
    -3.57
    ĸ
    -3.50
    ij
    -3.50
    ¶
    -3.47
    ©
    -3.43
      ↵ 
    -3.41
    <|padding|>
    -3.41
    <|outofrange|>
    -3.41
    ↵                                
    -3.41
    POSITIVE LOGITS
     reasons
    1.27
     explanation
    1.27
     custody
    1.24
    uous
    1.23
    ariate
    1.22
    olia
    1.21
    estones
    1.17
     consideration
    1.17
     oldest
    1.13
    ensive
    1.12
    Activations Density 1.294%

    No Known Activations