© 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. 26642
    Prev
    Next
    INDEX
    Explanations

    terms related to auditing and regulatory compliance in financial contexts

    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
    72
    +0.14
    0.8%
    24
    +0.13
    0.7%
    98
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    72
    +0.14
    0.09
    464
    +0.13
    0.03
    7
    +0.12
    -0.01
    Negative Logits
    :`
    -1.69
     affair
    -1.53
     quarrel
    -1.49
    iasis
    -1.44
     trouble
    -1.40
     lado
    -1.32
     _(
    -1.29
     bubbles
    -1.28
    lia
    -1.27
    ied
    -1.27
    POSITIVE LOGITS
    ľĵ
    3.55
    Ŀ
    3.54
    ł
    3.39
    Į
    3.33
    Ĥ¬
    3.25
    Ī
    3.21
    ¼
    3.13
    ¶
    3.11
    ´
    3.10
    »
    3.10
    Activations Density 4.154%

    No Known Activations