© 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. 1-RES-SM
    11. 27951
    Prev
    Next
    INDEX
    Explanations

    phrases related to software licensing 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/1-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.1.hook_resid_post
    Hook Layer
    1
    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
    98
    +0.16
    0.9%
    139
    +0.13
    0.7%
    482
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    26
    +0.16
    0.04
    252
    +0.13
    0.04
    265
    +0.12
    0.04
    Negative Logits
    §
    -1.94
    ®
    -1.90
    Ĺ
    -1.79
    ļ
    -1.74
    İ
    -1.66
    }}</
    -1.65
    ¡
    -1.64
    ²
    -1.61
    ł
    -1.61
    ¦
    -1.60
    POSITIVE LOGITS
     Redistributions
    1.74
    bsd
    1.71
     programs
    1.63
     cert
    1.54
     license
    1.53
     IMPLIED
    1.52
     Software
    1.52
     attorney
    1.51
     License
    1.49
    license
    1.49
    Activations Density 0.633%

    No Known Activations