© 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
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. Residuals
    9. 2-RES-SM
    11. 30274
    Prev
    Next
    INDEX
    Explanations

    words related to speed and pace

    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
    130
    +0.16
    0.9%
    477
    +0.13
    0.8%
    409
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    130
    +0.16
    0.03
    477
    +0.13
    0.03
    250
    +0.13
    0.03
    Negative Logits
    ĭ
    -3.43
    į
    -3.34
    ĻĤ
    -3.33
    ħ
    -3.31
    Ĭ
    -3.25
    ¾
    -3.24
    ĥ
    -3.18
    Į
    -3.18
    Ĩ
    -3.06
    ·¸
    -3.05
    POSITIVE LOGITS
     escal
    1.57
     oscillating
    1.57
     declining
    1.54
     ERROR
    1.52
     approaching
    1.47
     ageing
    1.42
     departed
    1.42
     migrating
    1.42
     GENERATED
    1.41
     deprec
    1.41
    Activations Density 0.084%

    No Known Activations