© 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. 13005
    Prev
    Next
    INDEX
    Explanations

    references to energy solutions and companies involved in energy services

    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
    231
    +0.16
    0.9%
    419
    +0.14
    0.8%
    325
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    66
    +0.16
    0.14
    231
    +0.14
    0.12
    134
    +0.12
    0.10
    Negative Logits
    ¯
    -1.81
    ĥ½
    -1.73
    ħ
    -1.66
    Ĥ¬
    -1.55
    »
    -1.53
    ³
    -1.51
    Ĥ
    -1.49
    aliana
    -1.49
    assisted
    -1.49
    Ĺ
    -1.46
    POSITIVE LOGITS
     Awards
    1.69
     Stadium
    1.49
     Champion
    1.40
     mog
    1.39
    urus
    1.39
     Sports
    1.38
     Industries
    1.37
     Airlines
    1.37
     standards
    1.37
     Access
    1.37
    Activations Density 2.666%

    No Known Activations