© 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. 4-RES-SM
    11. 10886
    Prev
    Next
    INDEX
    Explanations

    statistical terms related to pricing models or financial strategies

    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
    +0.28
    1.7%
    307
    +0.20
    1.1%
    137
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    291
    +0.28
    0.10
    137
    +0.20
    0.13
    145
    +0.14
    0.09
    Negative Logits
    ickets
    -1.51
    ÅĽci
    -1.47
    Õ¡
    -1.47
    pires
    -1.44
    ppo
    -1.43
    ños
    -1.39
    ÅĦ
    -1.39
    ениÑı
    -1.36
    àµį
    -1.34
    %.
    -1.33
    POSITIVE LOGITS
    following
    2.50
     following
    2.32
    oretical
    2.10
     simplest
    2.03
     usual
    2.03
     latter
    1.89
     aforementioned
    1.79
    obal
    1.76
     smallest
    1.75
     same
    1.74
    Activations Density 1.140%

    No Known Activations