© 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. 4-RES-SM
    11. 14135
    Prev
    Next
    INDEX
    Explanations

    connections and relationships within complex structures or systems

    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
    25
    +0.29
    1.7%
    466
    +0.18
    1.1%
    458
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    466
    +0.29
    0.10
    308
    +0.18
    0.05
    289
    +0.13
    0.04
    Negative Logits
    ij
    -3.33
    «
    -3.27
    ģ
    -3.16
    Ļ
    -3.10
    Ĥ
    -3.09
    ¢
    -2.97
    ł
    -2.94
    ¾
    -2.94
    Ľ
    -2.93
    ĺ
    -2.92
    POSITIVE LOGITS
     elsewhere
    2.55
     outdoors
    1.98
     abroad
    1.71
    pto
    1.60
    icago
    1.55
     throughout
    1.55
    bital
    1.52
     onward
    1.50
     during
    1.49
    YPT
    1.49
    Activations Density 0.683%

    No Known Activations