© 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. 28842
    Prev
    Next
    INDEX
    Explanations

    instances of the word "move" and its variations in various contexts, indicating a focus on movement or change

    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
    376
    +0.15
    0.8%
    156
    +0.12
    0.7%
    358
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    381
    +0.15
    0.03
    358
    +0.12
    0.04
    143
    +0.11
    0.03
    Negative Logits
    ĥ
    -3.00
    ĥ½
    -2.90
    ľĵ
    -2.81
    Į
    -2.80
    »¿
    -2.79
    §
    -2.70
    Ĥ¬
    -2.70
    Ī
    -2.68
    ª
    -2.62
    İ
    -2.54
    POSITIVE LOGITS
    able
    1.84
    pid
    1.69
    chip
    1.56
    legged
    1.49
    machine
    1.49
     slowly
    1.49
     forward
    1.49
     swiftly
    1.48
    ahead
    1.47
    dle
    1.46
    Activations Density 0.117%

    No Known Activations