© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 2-RES-SM
    11. 30187
    Prev
    Next
    INDEX
    Explanations

    financial and sales performance metrics

    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/2-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.2.hook_resid_post
    Hook Layer
    2
    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
    +0.19
    1.1%
    186
    +0.14
    0.8%
    462
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    186
    +0.19
    0.03
    462
    +0.14
    0.02
    335
    +0.10
    0.04
    Negative Logits
    ĻĤ
    -2.90
    º
    -2.47
    IJ
    -2.36
    ³
    -2.31
    ´
    -2.24
    -2.23
    -2.23
    ↵↵
    -2.23
    -2.23
    ↵            ↵
    -2.23
    POSITIVE LOGITS
     revenue
    1.95
     factor
    1.90
     taxes
    1.85
     income
    1.83
     forecast
    1.82
     tax
    1.81
    factor
    1.81
     margin
    1.76
     level
    1.74
     funnel
    1.73
    Activations Density 0.490%

    No Known Activations