© 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. 12969
    Prev
    Next
    INDEX
    Explanations

    references to appointments and positions within organizations

    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
    156
    +0.18
    1.0%
    168
    +0.14
    0.8%
    224
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    168
    +0.18
    0.13
    104
    +0.14
    -0.00
    340
    +0.13
    0.05
    Negative Logits
    ↵
    -2.22
    ↵            ↵
    -2.22
    -2.22
    -2.22
    ↵
    -2.22
    -2.22
    ↵
    -2.22
    ↵↵
    -2.22
    -2.22
    ↵
    -2.22
    POSITIVE LOGITS
     appoint
    3.09
     overse
    2.96
     staff
    2.95
     oversee
    2.92
     deputy
    2.86
     executive
    2.85
     committees
    2.84
     Executive
    2.82
     deleg
    2.80
     Staff
    2.75
    Activations Density 3.039%

    No Known Activations