© 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. 13695
    Prev
    Next
    INDEX
    Explanations

    phrases related to software licensing and distribution 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
    320
    +0.13
    0.7%
    233
    +0.12
    0.7%
    391
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    391
    +0.13
    0.03
    445
    +0.12
    0.02
    74
    +0.12
    0.03
    Negative Logits
    ĥ½
    -2.20
    »¿
    -2.18
    į
    -2.06
    Ĩ
    -2.01
    ·¸
    -2.00
    Į
    -1.97
    ®
    -1.94
    ĩ
    -1.91
    ¢
    -1.89
    Ń
    -1.87
    POSITIVE LOGITS
    ÂĶ
    1.54
     Âĵ
    1.46
    Âĵ
    1.33
     grant
    1.32
     Norton
    1.31
    sible
    1.31
     Â
    1.31
    minded
    1.30
     award
    1.30
     Bankruptcy
    1.28
    Activations Density 0.179%

    No Known Activations