© 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. 2-RES-SM
    11. 26833
    Prev
    Next
    INDEX
    Explanations

    elements related to asset management and financial transactions

    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
    326
    +0.15
    0.8%
    307
    +0.12
    0.7%
    127
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.15
    0.04
    127
    +0.12
    0.15
    100
    +0.12
    0.11
    Negative Logits
    tees
    -1.72
    amis
    -1.61
     jobs
    -1.55
    ades
    -1.45
     alike
    -1.40
    weed
    -1.34
    eu
    -1.32
     respectively
    -1.31
    bsd
    -1.31
    artan
    -1.29
    POSITIVE LOGITS
    ·
    2.41
    ½
    2.32
    ²
    2.23
    ¼
    2.17
    Ń
    2.15
    ĥ½
    2.11
    µ
    2.10
    ®
    2.09
    ¹
    2.06
    ¸
    2.05
    Activations Density 5.242%

    No Known Activations