© 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. 27678
    Prev
    Next
    INDEX
    Explanations

    terms and phrases associated with administrative processes and classifications

    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
    316
    +0.11
    0.6%
    485
    +0.11
    0.6%
    438
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    68
    +0.11
    0.07
    445
    +0.11
    0.03
    441
    +0.11
    0.01
    Negative Logits
    aws
    -1.40
    >=
    -1.36
     holds
    -1.32
    ||
    -1.30
     won
    -1.29
    -1.28
    NS
    -1.27
    includes
    -1.27
     called
    -1.26
     she
    -1.26
    POSITIVE LOGITS
    Ĵ
    2.85
    Ĭ
    2.68
    ī
    2.58
    ĭ
    2.58
    IJ
    2.57
    ¶
    2.53
    ¡
    2.47
    ĥ½
    2.47
    ģ
    2.47
    £
    2.40
    Activations Density 1.169%

    No Known Activations