© 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. 27121
    Prev
    Next
    INDEX
    Explanations

    intensifiers that convey a high degree of quality or effectiveness

    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
    78
    +0.17
    1.0%
    394
    +0.13
    0.7%
    29
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    78
    +0.17
    0.02
    375
    +0.13
    0.02
    394
    +0.13
    0.03
    Negative Logits
    ŀ
    -2.19
    hering
    -1.73
    herty
    -1.70
    IJ
    -1.68
    ices
    -1.63
    iers
    -1.63
    ils
    -1.62
    ulin
    -1.62
    uins
    -1.61
    ¥
    -1.58
    POSITIVE LOGITS
     enough
    1.87
     ranked
    1.67
     (>
    1.50
     Lear
    1.48
     (\>
    1.44
     valued
    1.43
     graded
    1.43
    bury
    1.43
     populated
    1.43
     (âī¥
    1.43
    Activations Density 0.069%

    No Known Activations