© 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. 10915
    Prev
    Next
    INDEX
    Explanations

    references to software licenses and usage permissions

    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
    302
    +0.12
    0.7%
    57
    +0.11
    0.6%
    391
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    328
    +0.12
    0.02
    57
    +0.11
    0.03
    302
    +0.10
    0.03
    Negative Logits
     nesting
    -1.56
    oretic
    -1.42
    oret
    -1.40
    ocrats
    -1.37
     correlations
    -1.36
     abundances
    -1.36
     calculations
    -1.35
     favour
    -1.34
    ).](
    -1.32
     consensus
    -1.32
    POSITIVE LOGITS
    ī
    2.38
    µ
    2.25
    ¡
    2.08
    ´
    1.99
    ħ
    1.95
    ¥
    1.94
    ±
    1.91
    Ī
    1.89
    ³
    1.89
    ·¸
    1.88
    Activations Density 0.080%

    No Known Activations