© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. Residuals
    9. 1-RES-SM
    11. 27609
    Prev
    Next
    INDEX
    Explanations

    questions beginning with "which"

    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/1-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.1.hook_resid_post
    Hook Layer
    1
    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
    478
    +0.14
    0.8%
    319
    +0.13
    0.7%
    262
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    39
    +0.14
    0.07
    319
    +0.13
    0.07
    262
    +0.11
    0.06
    Negative Logits
     anytime
    -1.73
    atsu
    -1.43
    åĬ¡
    -1.42
     anywhere
    -1.40
     whom
    -1.34
    FIG
    -1.34
     who
    -1.31
     whatsoever
    -1.31
     wherever
    -1.30
    imiento
    -1.30
    POSITIVE LOGITS
    į
    3.07
    Į
    3.01
    ¹
    2.70
    ½
    2.53
    §
    2.41
    ³
    2.33
    IJ
    2.32
    ¨
    2.32
    Ī
    2.31
    ²
    2.30
    Activations Density 0.169%

    No Known Activations