© 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. 28102
    Prev
    Next
    INDEX
    Explanations

    instances of the word "remember" and its variations

    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
    100
    +0.14
    0.8%
    23
    +0.13
    0.7%
    30
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    30
    +0.14
    0.03
    100
    +0.13
    0.03
    382
    +0.11
    0.03
    Negative Logits
    «
    -3.40
    ¶
    -3.16
    į
    -3.14
    ¾
    -3.14
    Ĩ
    -2.93
    ī
    -2.92
    Ń
    -2.83
    º
    -2.83
    Ħ
    -2.82
    £
    -2.74
    POSITIVE LOGITS
     how
    1.77
     old
    1.76
     nothing
    1.61
    ocene
    1.59
     ownership
    1.59
     sight
    1.58
     something
    1.56
     everything
    1.54
     what
    1.54
     occasion
    1.53
    Activations Density 0.189%

    No Known Activations