© 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. 4-RES-SM
    11. 10700
    Prev
    Next
    INDEX
    Explanations

    names or proper nouns

    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/4-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.4.hook_resid_post
    Hook Layer
    4
    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
    70
    +0.14
    0.8%
    350
    +0.14
    0.8%
    436
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    350
    +0.14
    0.02
    410
    +0.14
    0.02
    98
    +0.12
    0.01
    Negative Logits
     comparison
    -1.56
    ivity
    -1.43
     standpoint
    -1.38
    USE
    -1.38
    USY
    -1.38
    OLOG
    -1.38
     control
    -1.36
    ytics
    -1.36
    IFIC
    -1.35
    ively
    -1.34
    POSITIVE LOGITS
    kinson
    2.69
    ming
    2.38
    shire
    2.21
    kes
    1.95
    helm
    1.93
    cox
    1.90
    fried
    1.89
    mot
    1.86
    mers
    1.86
    lys
    1.80
    Activations Density 0.149%

    No Known Activations