© 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. 13136
    Prev
    Next
    INDEX
    Explanations

    expressions of discontent or negativity

    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
    419
    +0.14
    0.8%
    380
    +0.13
    0.7%
    115
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    50
    +0.14
    0.02
    469
    +0.13
    0.03
    380
    +0.13
    0.02
    Negative Logits
    astro
    -1.78
    zyk
    -1.77
    imore
    -1.76
    ictionaries
    -1.76
    rones
    -1.66
    ook
    -1.63
    icks
    -1.62
    icians
    -1.60
    tis
    -1.60
    amas
    -1.59
    POSITIVE LOGITS
    IJ
    1.81
    Ĥ
    1.69
    ¬
    1.54
     ment
    1.50
    ¦
    1.48
    ¤
    1.46
    dated
    1.45
     regulated
    1.45
    crystall
    1.44
    ¶
    1.43
    Activations Density 0.087%

    No Known Activations