© 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. 31415
    Prev
    Next
    INDEX
    Explanations

    references to location-based behaviors and connections

    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
    323
    +0.17
    1.0%
    263
    +0.17
    1.0%
    489
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    323
    +0.17
    0.06
    78
    +0.17
    0.06
    202
    +0.12
    0.07
    Negative Logits
    ĻĤ
    -3.18
    Ļª
    -3.15
    ĨĴ
    -2.74
    ¿½
    -2.66
    ¬
    -2.61
    ĵ
    -2.56
    £
    -2.50
    ®
    -2.49
    Ĺ
    -2.45
    ¿
    -2.38
    POSITIVE LOGITS
     excellence
    1.47
     Discovery
    1.42
    \]](
    1.41
     precision
    1.38
     consistency
    1.37
     dispense
    1.34
     effect
    1.32
    ovsk
    1.31
    ness
    1.29
     symmetry
    1.29
    Activations Density 3.196%

    No Known Activations