© 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. 1-RES-SM
    11. 28555
    Prev
    Next
    INDEX
    Explanations

    references to familial relationships, particularly involving daughters

    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
    156
    +0.15
    0.9%
    334
    +0.12
    0.7%
    492
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    87
    +0.15
    0.03
    410
    +0.12
    0.03
    328
    +0.12
    0.04
    Negative Logits
    ĵ
    -3.73
    ĸ
    -2.99
    ĥ½
    -2.90
    ĺ
    -2.87
    ³
    -2.80
    -2.80
    <|outofrange|>
    -2.80
    ↵↵
    -2.80
    ↵
    -2.80
    čč
    -2.80
    POSITIVE LOGITS
     herself
    2.26
    hood
    1.76
    folk
    1.74
    arial
    1.61
    icorn
    1.59
    liness
    1.57
     Nina
    1.55
    lies
    1.52
    forth
    1.51
    hesis
    1.50
    Activations Density 0.214%

    No Known Activations