© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. Residuals
    9. 1-RES-SM
    11. 25849
    Prev
    Next
    INDEX
    Explanations

    repeated conjunctions and connectors in a text

    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/1-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.1.hook_resid_post
    Hook Layer
    1
    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
    118
    +0.13
    0.7%
    76
    +0.13
    0.7%
    127
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    494
    +0.13
    0.13
    209
    +0.13
    0.11
    389
    +0.13
    0.10
    Negative Logits
     yourselves
    -2.06
     (@
    -1.73
     yourself
    -1.64
    Īĺ
    -1.57
     nature
    -1.55
     ('
    -1.53
     strength
    -1.51
    zer
    -1.50
    unes
    -1.49
    ungen
    -1.49
    POSITIVE LOGITS
     "</
    1.48
    rew
    1.43
    nai
    1.32
     punct
    1.28
     degenerative
    1.28
    ATE
    1.28
    riev
    1.27
     obesity
    1.26
    '">
    1.26
     acet
    1.25
    Activations Density 1.100%

    No Known Activations