© 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. 12909
    Prev
    Next
    INDEX
    Explanations

    phrases related to licenses and their terms

    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
    499
    +0.13
    0.8%
    24
    +0.12
    0.7%
    143
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    499
    +0.13
    0.02
    171
    +0.12
    0.01
    192
    +0.10
    0.01
    Negative Logits
    Ĭ
    -1.99
    Ķ
    -1.92
     respectively
    -1.88
    ľ
    -1.86
    ¢
    -1.82
    ļ
    -1.79
    Ļ
    -1.78
    ķ
    -1.76
    Ĺ
    -1.66
    Ł
    -1.65
    POSITIVE LOGITS
     Redistributions
    1.98
     publication
    1.73
     COPYRIGHT
    1.72
    :")
    1.72
     notation
    1.71
    ↵	↵
    1.66
     disclaimer
    1.56
    ário
    1.56
     GNU
    1.53
     anonym
    1.51
    Activations Density 0.107%

    No Known Activations