© 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. 28785
    Prev
    Next
    INDEX
    Explanations

    phrases related to waking and sleeping states

    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
    290
    +0.14
    0.8%
    162
    +0.12
    0.7%
    151
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    290
    +0.14
    0.02
    162
    +0.12
    0.02
    115
    +0.11
    0.01
    Negative Logits
     Copyright
    -1.85
    .'"
    -1.71
     harmed
    -1.49
     deletion
    -1.45
    .<
    -1.44
    ,'"
    -1.44
     hereto
    -1.42
    substack
    -1.41
     prejudiced
    -1.40
     license
    -1.36
    POSITIVE LOGITS
    ful
    2.28
    ingly
    2.04
    fulness
    2.01
    weather
    1.95
    »
    1.93
    nut
    1.92
    ety
    1.90
    hurst
    1.87
    nuts
    1.80
    etable
    1.67
    Activations Density 0.128%

    No Known Activations