© 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. 24950
    Prev
    Next
    INDEX
    Explanations

    occurrences of specific foreign words or phrases

    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
    +0.20
    1.1%
    111
    +0.13
    0.7%
    321
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.20
    0.04
    271
    +0.13
    0.01
    156
    +0.12
    0.03
    Negative Logits
    hin
    -2.01
    ĥ½
    -1.55
    athing
    -1.43
     trash
    -1.36
     dropping
    -1.33
    ét
    -1.32
    asted
    -1.31
    iance
    -1.29
    rated
    -1.28
    odies
    -1.28
    POSITIVE LOGITS
     Valley
    1.76
    genstein
    1.59
    mare
    1.53
     win
    1.51
    nement
    1.50
    nai
    1.46
    ni
    1.46
    vent
    1.45
    iewicz
    1.44
    oslov
    1.44
    Activations Density 0.158%

    No Known Activations