© 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. 1-RES-SM
    11. 28957
    Prev
    Next
    INDEX
    Explanations

    technical terms and jargon related to finance and assets

    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/1-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.1.hook_resid_post
    Hook Layer
    1
    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
    268
    +0.12
    0.7%
    12
    +0.12
    0.6%
    111
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    268
    +0.12
    0.04
    17
    +0.12
    0.02
    379
    +0.11
    0.05
    Negative Logits
    hes
    -1.96
     stri
    -1.60
    preced
    -1.56
    past
    -1.52
     Workers
    -1.46
    bent
    -1.45
    one
    -1.44
     petitioners
    -1.41
    ere
    -1.41
    ising
    -1.40
    POSITIVE LOGITS
     properties
    1.62
    ouin
    1.57
    ael
    1.53
    Camera
    1.48
    Ĵ
    1.43
    ĥ½
    1.39
     aside
    1.38
     colors
    1.35
     stats
    1.35
    onucle
    1.34
    Activations Density 0.620%

    No Known Activations