© 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. 4-RES-SM
    11. 10013
    Prev
    Next
    INDEX
    Explanations

    terminology related to financial and business 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/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
    225
    +0.11
    0.6%
    274
    +0.11
    0.6%
    269
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    421
    +0.11
    0.06
    269
    +0.11
    0.07
    225
    +0.11
    0.05
    Negative Logits
     ([@
    -2.88
     –
    -2.82
     '$
    -2.40
    )',
    -2.36
    ')
    -2.24
     '
    -2.19
     –,
    -2.19
     ('
    -2.18
    ,--
    -2.11
    ––
    -2.08
    POSITIVE LOGITS
    &#
    5.13
     Âĵ
    4.90
    .\[[@
    4.86
    â
    4.85
    ÃĤ
    4.74
    ÂĶ
    4.67
    č
    4.61
    ÂĴ
    4.52
     [âĢ¦]
    4.41
     â
    4.39
    Activations Density 1.272%

    No Known Activations