© 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
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. Residuals
    5. 2-RES-SM
    6. 31793
    Prev
    Next
    INDEX
    Explanations

    locations and associated numerical identifiers or values

    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/2-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.2.hook_resid_post
    Hook Layer
    2
    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
    248
    +0.11
    0.6%
    370
    +0.11
    0.6%
    46
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    248
    +0.11
    0.05
    46
    +0.11
    0.04
    319
    +0.11
    0.04
    Negative Logits
    {}{
    -1.90
     neut
    -1.61
    {
    -1.58
    '):
    -1.56
    {\
    -1.55
     MeV
    -1.55
     {}
    -1.51
    {}\
    -1.41
     Cambridge
    -1.40
    rieve
    -1.39
    POSITIVE LOGITS
    FW
    1.60
    itian
    1.57
    gow
    1.54
    igator
    1.49
    cki
    1.49
    case
    1.48
    ีà¹Ī
    1.46
    erated
    1.44
    à¹ī
    1.41
    ģ
    1.39
    Activations Density 0.328%

    No Known Activations