© 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. 25125
    Prev
    Next
    INDEX
    Explanations

    words related to awareness and consciousness

    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
    369
    +0.15
    0.9%
    164
    +0.14
    0.8%
    484
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    40
    +0.15
    0.03
    477
    +0.14
    0.03
    339
    +0.11
    0.02
    Negative Logits
    iture
    -1.67
    MSO
    -1.47
     course
    -1.46
    URAL
    -1.45
     colon
    -1.44
    CDATA
    -1.41
    abouts
    -1.39
     NW
    -1.39
     MSD
    -1.35
     relate
    -1.34
    POSITIVE LOGITS
    esome
    2.22
    indo
    1.99
    orld
    1.95
    deen
    1.84
    areness
    1.79
    yer
    1.71
    lessly
    1.70
    ols
    1.65
    etz
    1.65
    alt
    1.64
    Activations Density 0.105%

    No Known Activations