© 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. 12633
    Prev
    Next
    INDEX
    Explanations

    references to consumer behavior and market trends

    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
    186
    +0.22
    1.3%
    406
    +0.15
    0.9%
    108
    +0.15
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    186
    +0.22
    0.12
    108
    +0.15
    0.16
    455
    +0.15
    0.15
    Negative Logits
    ī
    -3.65
    ĥ½
    -3.60
    ³
    -3.58
    ¥
    -3.58
    ĻĤ
    -3.56
    ĸ´
    -3.51
    IJ
    -3.40
    °
    -3.35
    ¯
    -3.32
    ¦
    -3.31
    POSITIVE LOGITS
     flock
    2.07
     vent
    1.86
     whom
    1.73
     their
    1.72
     voluntarily
    1.72
     themselves
    1.66
     welfare
    1.66
     respons
    1.63
     habit
    1.61
     pockets
    1.58
    Activations Density 5.000%

    No Known Activations