© 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 EvalsExportsinterp-engineNEWAPI 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. 24554
    Prev
    Next
    INDEX
    Explanations

    instances of "100 percent" in various contexts, particularly emphasizing completeness or totality

    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
    408
    +0.15
    0.8%
    477
    +0.14
    0.8%
    130
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.15
    0.06
    436
    +0.14
    0.06
    130
    +0.12
    0.05
    Negative Logits
    ikov
    -1.79
    rien
    -1.52
    aken
    -1.47
     theirs
    -1.42
    ising
    -1.40
    ynes
    -1.40
    ization
    -1.37
     sovereignty
    -1.34
     inevitable
    -1.33
     wrought
    -1.32
    POSITIVE LOGITS
    %"
    1.98
    ths
    1.83
    Hz
    1.75
     Hz
    1.74
    \%
    1.72
     percent
    1.71
    %;
    1.68
    %,
    1.67
     tracks
    1.64
    meter
    1.62
    Activations Density 0.404%

    No Known Activations