© 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. 13964
    Prev
    Next
    INDEX
    Explanations

    technical terms related to aerospace and military operations

    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
    286
    +0.13
    0.7%
    315
    +0.11
    0.6%
    442
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    189
    +0.13
    0.07
    45
    +0.11
    0.05
    437
    +0.11
    0.06
    Negative Logits
    Ļª
    -1.95
    IJ
    -1.87
    ļ
    -1.80
     periodontal
    -1.77
     Privacy
    -1.76
     connective
    -1.71
    ĻĤ
    -1.69
    »¿
    -1.68
    ¹
    -1.68
    ľĵ
    -1.65
    POSITIVE LOGITS
     flight
    2.52
     aboard
    2.42
     fleet
    2.36
     flying
    2.34
     flown
    2.33
     ship
    2.29
     aircraft
    2.13
     USS
    2.13
     helicopter
    2.09
     cruise
    2.09
    Activations Density 0.775%

    No Known Activations