© 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. 25702
    Prev
    Next
    INDEX
    Explanations

    technical terms and commands related to computer systems and software

    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
    23
    +0.28
    1.6%
    478
    +0.14
    0.8%
    6
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    376
    +0.28
    0.05
    148
    +0.14
    0.04
    6
    +0.14
    0.08
    Negative Logits
    assic
    -1.90
    neys
    -1.85
    ados
    -1.65
    sworth
    -1.63
     era
    -1.61
    ERY
    -1.60
    liche
    -1.54
    nell
    -1.54
    izione
    -1.52
    ades
    -1.48
    POSITIVE LOGITS
    upon
    1.77
     hereto
    1.64
    between
    1.58
     '<
    1.56
     hers
    1.53
    rangle
    1.52
    orously
    1.49
    exists
    1.49
     Redistributions
    1.43
     notation
    1.38
    Activations Density 3.309%

    No Known Activations