© 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. 14018
    Prev
    Next
    INDEX
    Explanations

    references to programming code and documentation

    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
    71
    +0.12
    0.7%
    155
    +0.11
    0.6%
    431
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    451
    +0.12
    -0.01
    78
    +0.11
    -0.02
    59
    +0.10
    0.02
    Negative Logits
    ceptions
    -1.59
     maintenance
    -1.55
    inki
    -1.39
     drinks
    -1.36
    "}](#
    -1.36
     emergencies
    -1.34
    oxic
    -1.33
    ctic
    -1.33
     drills
    -1.33
    Calendar
    -1.32
    POSITIVE LOGITS
    ”)
    1.99
    ↵↵↵↵
    1.81
    ↵↵↵↵↵
    1.80
    .”).
    1.77
    ”).
    1.74
    .”
    1.74
    irected
    1.73
    ↵↵↵↵↵↵↵
    1.69
    ↵↵↵↵↵↵↵↵
    1.68
    ↵↵↵
    1.57
    Activations Density 0.456%

    No Known Activations