© 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. 13551
    Prev
    Next
    INDEX
    Explanations

    phrases reflecting monetary values 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/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
    156
    +0.38
    2.3%
    137
    +0.14
    0.9%
    240
    +0.14
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    291
    +0.38
    0.13
    10
    +0.14
    0.14
    145
    +0.14
    0.10
    Negative Logits
    "}](#
    -1.78
    ãĥ¼ãĤ¸
    -1.76
    ãĥ«
    -1.63
    ãĥ¼ãĥī
    -1.62
    ãĥ¥
    -1.60
    ruptcy
    -1.57
    ÑĤа
    -1.57
    ãĥĥãĥĪ
    -1.56
    theorem
    -1.53
    å¼ı
    -1.51
    POSITIVE LOGITS
     entire
    2.47
     slightest
    2.35
     desired
    2.31
     same
    2.20
     aforementioned
    2.19
     actual
    2.12
     respective
    2.11
     entirety
    2.00
    rapeut
    1.98
     latter
    1.92
    Activations Density 1.451%

    No Known Activations