© 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. 28417
    Prev
    Next
    INDEX
    Explanations

    expressions related to positive outcomes or news

    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
    489
    +0.15
    0.9%
    62
    +0.15
    0.9%
    397
    +0.15
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.15
    0.10
    397
    +0.15
    0.06
    489
    +0.15
    0.07
    Negative Logits
    :&
    -1.77
    acket
    -1.51
    :</
    -1.46
     suppose
    -1.40
     intend
    -1.36
     Lik
    -1.36
    adesh
    -1.36
     identically
    -1.33
    ?).
    -1.29
     embol
    -1.28
    POSITIVE LOGITS
    eries
    1.85
    rapy
    1.52
     aspects
    1.52
    ERN
    1.47
     walls
    1.46
     aspect
    1.44
     sides
    1.43
     market
    1.42
    teenth
    1.41
     bones
    1.40
    Activations Density 0.782%

    No Known Activations