© 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. 30677
    Prev
    Next
    INDEX
    Explanations

    references to actions, techniques, or judgments related to education, guidance, or performance

    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
    287
    +0.13
    0.7%
    192
    +0.12
    0.7%
    77
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    408
    +0.13
    0.09
    256
    +0.12
    0.12
    407
    +0.11
    0.09
    Negative Logits
    ŀ
    -3.39
    ¿
    -3.31
    ²
    -3.15
    ľĵ
    -3.13
    ĨĴ
    -3.07
    ³
    -3.06
    ¾
    -3.04
    Į
    -3.03
    ĻĤ
    -2.95
    Ļª
    -2.94
    POSITIVE LOGITS
     themselves
    2.30
     together
    1.70
    adies
    1.68
    Conclusions
    1.42
     respective
    1.41
     they
    1.40
    ]]>
    1.39
     side
    1.39
    Discussion
    1.39
    They
    1.37
    Activations Density 3.299%

    No Known Activations