© 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. 30810
    Prev
    Next
    INDEX
    Explanations

    code-related terms and identifiers

    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
    156
    +0.27
    1.6%
    17
    +0.18
    1.1%
    369
    +0.18
    1.1%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    17
    +0.27
    0.03
    379
    +0.18
    0.11
    369
    +0.18
    0.05
    Negative Logits
    )[@
    -1.89
     ensued
    -1.89
    )^[@
    -1.57
     ).
    -1.57
    )](#
    -1.56
     preponderance
    -1.52
    )</
    -1.52
    )\]
    -1.51
    .)
    -1.49
    .[@
    -1.47
    POSITIVE LOGITS
    ³
    2.02
    Ļª
    2.02
    ª
    1.90
    Ģ
    1.80
    ĻĤ
    1.79
    ľĵ
    1.62
    »
    1.62
     chin
    1.61
    ij
    1.59
    Ĵ
    1.57
    Activations Density 0.959%

    No Known Activations