© 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. 28531
    Prev
    Next
    INDEX
    Explanations

    mentions of various types of magazines and publications

    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
    156
    +0.23
    1.3%
    507
    +0.14
    0.8%
    412
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    38
    +0.23
    0.02
    507
    +0.14
    0.02
    242
    +0.12
    0.02
    Negative Logits
     possible
    -1.64
     stably
    -1.61
     suppose
    -1.57
     autosomal
    -1.46
     schizophren
    -1.45
     couples
    -1.45
     heart
    -1.44
     conceivable
    -1.44
     yours
    -1.42
     hers
    -1.39
    POSITIVE LOGITS
    matic
    1.98
    brush
    1.87
    oon
    1.84
    ious
    1.77
    ios
    1.70
    ulation
    1.70
    meric
    1.67
    citation
    1.65
    80211
    1.64
    pub
    1.62
    Activations Density 0.143%

    No Known Activations