© 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. 25602
    Prev
    Next
    INDEX
    Explanations

    references to scientific studies or citations in texts

    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
    +0.19
    1.1%
    397
    +0.13
    0.7%
    111
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.19
    0.06
    271
    +0.13
    0.03
    156
    +0.13
    0.03
    Negative Logits
    ”?
    -1.73
    \",
    -1.61
    ”:
    -1.60
     coverage
    -1.57
     connections
    -1.49
    ieve
    -1.48
    lan
    -1.46
    izations
    -1.45
    ants
    -1.44
    izers
    -1.44
    POSITIVE LOGITS
    sted
    1.63
     cref
    1.61
    pone
    1.54
    CR
    1.52
     ende
    1.51
    RSOS
    1.50
    bard
    1.50
    ...)
    1.49
    RSP
    1.47
    wasysym
    1.46
    Activations Density 0.194%

    No Known Activations