© 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. 28794
    Prev
    Next
    INDEX
    Explanations

    mentions of benefits or advantages

    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
    174
    +0.14
    0.8%
    386
    +0.13
    0.7%
    73
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    386
    +0.14
    0.02
    174
    +0.13
    0.02
    73
    +0.12
    0.01
    Negative Logits
    shore
    -2.00
    tig
    -1.75
     how
    -1.68
    ness
    -1.51
    dings
    -1.45
     diseases
    -1.45
     slightest
    -1.43
    orms
    -1.41
     mammals
    -1.41
     animals
    -1.41
    POSITIVE LOGITS
    pective
    2.63
    pero
    1.83
    ÃŃf
    1.74
    pered
    1.71
    ului
    1.63
    ellers
    1.62
    ī
    1.57
    cu
    1.56
    ilion
    1.52
    aho
    1.51
    Activations Density 0.087%

    No Known Activations