© 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. 2-RES-SM
    11. 10356
    Prev
    Next
    INDEX
    Explanations

    keywords related to fertility clinics and assisted reproductive technology

    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
    427
    +0.15
    0.9%
    143
    +0.13
    0.8%
    161
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    427
    +0.15
    0.10
    143
    +0.13
    0.08
    351
    +0.13
    0.11
    Negative Logits
    ostics
    -1.67
    iki
    -1.49
     atmosphere
    -1.49
    doibase
    -1.42
    ostomy
    -1.41
    OOST
    -1.33
     leak
    -1.31
    itor
    -1.31
    lt
    -1.31
    ostic
    -1.28
    POSITIVE LOGITS
    «
    2.41
    Ģ
    2.35
    ĻĤ
    2.35
    ļ
    2.33
    ·¸
    2.29
    Īĺ
    2.20
    IJ
    2.19
    ¦
    2.19
    Ķ
    2.11
    ģ
    2.10
    Activations Density 4.646%

    No Known Activations