© 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. 1-RES-SM
    11. 28091
    Prev
    Next
    INDEX
    Explanations

    terms related to financial and economic concepts

    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
    395
    +0.15
    0.8%
    231
    +0.14
    0.8%
    419
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    395
    +0.15
    0.11
    143
    +0.14
    0.09
    476
    +0.12
    0.11
    Negative Logits
    §
    -2.59
    Ĩ
    -2.40
    ĺ
    -2.31
    Ļª
    -2.28
    į
    -2.15
    ĥ½
    -2.12
    ¸
    -2.06
    Ī
    -2.05
    ©
    -2.05
    »¿
    -2.03
    POSITIVE LOGITS
     alike
    2.74
     buttons
    1.73
     technologies
    1.55
     therefrom
    1.53
     protocols
    1.51
     formats
    1.49
    ware
    1.45
    )."
    1.45
     designs
    1.45
    craft
    1.43
    Activations Density 1.559%

    No Known Activations