© 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 EvalsExportsAPI 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. 26405
    Prev
    Next
    INDEX
    Explanations

    mentions of temperature in various contexts

    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
    +0.17
    1.0%
    269
    +0.14
    0.8%
    500
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    269
    +0.17
    0.03
    167
    +0.14
    0.02
    500
    +0.12
    0.02
    Negative Logits
    ł
    -2.04
     hers
    -2.04
    sburg
    -2.00
    ureus
    -1.83
    Ĥ¬
    -1.80
    ĸ´
    -1.79
    thood
    -1.77
    mes
    -1.75
    ment
    -1.73
    Īĺ
    -1.70
    POSITIVE LOGITS
     ranges
    1.84
     tolerance
    1.76
     gradient
    1.66
     rises
    1.65
    etting
    1.60
     adaptation
    1.57
     deteriorated
    1.53
     increases
    1.51
     range
    1.50
    banks
    1.46
    Activations Density 0.066%

    No Known Activations