© 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. 27726
    Prev
    Next
    INDEX
    Explanations

    coding syntax, particularly involving types and functions

    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
    30
    +0.13
    0.7%
    192
    +0.11
    0.6%
    247
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    249
    +0.13
    0.06
    136
    +0.11
    -0.03
    93
    +0.10
    0.06
    Negative Logits
    ĸ´
    -4.26
    ¹
    -3.82
    »
    -3.81
    ¿
    -3.69
    ½
    -3.67
    ¾
    -3.65
    ³
    -3.62
    ĭ
    -3.60
    ¦
    -3.56
    Ĥ
    -3.56
    POSITIVE LOGITS
     percentage
    1.71
     BGCOLOR
    1.52
    estine
    1.51
     proportion
    1.50
    limits
    1.50
     ÎĶ
    1.49
    ITION
    1.48
     widths
    1.47
     percentages
    1.47
    ORDER
    1.46
    Activations Density 1.741%

    No Known Activations