© 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. 25884
    Prev
    Next
    INDEX
    Explanations

    references to time-related concepts

    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
    434
    +0.15
    0.8%
    457
    +0.12
    0.7%
    74
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    434
    +0.15
    0.01
    92
    +0.12
    0.01
    171
    +0.10
    0.02
    Negative Logits
    ĻĤ
    -1.59
     mistaken
    -1.51
    ======
    -1.49
    iquit
    -1.48
    ISHED
    -1.39
    iqu
    -1.39
    AY
    -1.38
     isolated
    -1.38
    derr
    -1.37
     lonely
    -1.36
    POSITIVE LOGITS
    ña
    1.90
    works
    1.84
    wright
    1.80
    coin
    1.77
    ÅĽ
    1.76
    añ
    1.75
    cias
    1.71
    finder
    1.69
    zone
    1.68
     brings
    1.66
    Activations Density 0.131%

    No Known Activations