© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. Residuals
    5. 1-RES-SM
    6. 26673
    Prev
    Next
    INDEX
    Explanations

    references to cloud services and architecture

    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
    +0.18
    1.1%
    444
    +0.12
    0.7%
    173
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    45
    +0.18
    0.02
    113
    +0.12
    0.02
    444
    +0.12
    0.02
    Negative Logits
     slightest
    -1.73
     great
    -1.60
     definite
    -1.58
     usual
    -1.57
     acute
    -1.57
    uppose
    -1.56
     saline
    -1.55
     extreme
    -1.51
     unconscious
    -1.50
     happ
    -1.49
    POSITIVE LOGITS
    flare
    2.48
    hart
    2.19
    break
    2.05
    works
    2.01
    notes
    1.97
    worth
    1.94
    burst
    1.90
    ings
    1.89
    bourne
    1.88
    ÃŃa
    1.87
    Activations Density 0.092%

    No Known Activations