© 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. 28279
    Prev
    Next
    INDEX
    Explanations

    terms related to programming interfaces

    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
    156
    +0.16
    0.9%
    130
    +0.12
    0.7%
    507
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    250
    +0.16
    0.02
    179
    +0.12
    0.02
    501
    +0.12
    0.01
    Negative Logits
    ľĵ
    -2.19
    Ģ
    -2.13
    ĻĤ
    -2.12
    ĥ
    -2.05
    ´
    -2.02
    ¤
    -2.00
    ©
    -1.99
    ĥ½
    -1.97
    Ĥ¬
    -1.91
    »¿
    -1.90
    POSITIVE LOGITS
     interface
    1.76
     between
    1.76
     interfaces
    1.74
    ization
    1.66
    rically
    1.63
    ility
    1.62
    rient
    1.61
    ivation
    1.61
    uitively
    1.58
    {}{
    1.56
    Activations Density 0.109%

    No Known Activations