© 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. 4-RES-SM
    11. 11788
    Prev
    Next
    INDEX
    Explanations

    references to walls or similar structures

    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
    89
    +0.15
    0.8%
    444
    +0.15
    0.8%
    466
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    194
    +0.15
    0.02
    373
    +0.15
    0.03
    212
    +0.14
    0.02
    Negative Logits
    leton
    -1.93
    ubicin
    -1.77
    xico
    -1.67
    iries
    -1.66
    zia
    -1.59
    ality
    -1.56
     adults
    -1.55
    aldehyde
    -1.54
    letons
    -1.49
     sleepy
    -1.48
    POSITIVE LOGITS
    paper
    3.46
    papers
    3.29
    ij
    2.96
    İ
    2.75
    ĺ
    2.73
    flower
    2.72
    ¼
    2.70
    µ
    2.69
    £
    2.63
    ed
    2.59
    Activations Density 0.187%

    No Known Activations