© 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. 12563
    Prev
    Next
    INDEX
    Explanations

    terms related to sales and financial 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/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
    492
    +0.12
    0.7%
    262
    +0.12
    0.7%
    378
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    262
    +0.12
    0.04
    186
    +0.12
    0.04
    125
    +0.12
    0.04
    Negative Logits
    fered
    -1.91
     bathing
    -1.74
    fts
    -1.71
    vern
    -1.60
    upon
    -1.58
    ukary
    -1.58
    ICU
    -1.57
    unnumbered
    -1.53
    else
    -1.52
    nea
    -1.51
    POSITIVE LOGITS
    Ķ
    2.53
    manship
    2.46
    ĺ
    2.42
     tax
    2.42
    ¬
    2.35
     funnel
    2.33
     taxes
    2.13
     sales
    2.09
    Ī
    2.04
     prices
    2.02
    Activations Density 0.466%

    No Known Activations