© 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. 12404
    Prev
    Next
    INDEX
    Explanations

    phrases related to software installation and updates

    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
    +0.15
    0.8%
    159
    +0.12
    0.7%
    146
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    146
    +0.15
    0.06
    176
    +0.12
    0.08
    409
    +0.12
    0.08
    Negative Logits
    «
    -3.46
    ĥ
    -3.36
    ĵ
    -3.34
    ±
    -3.26
    ij
    -3.23
    ¯
    -3.22
    ģ
    -3.21
    §
    -3.19
    Ļ
    -3.19
    ·
    -3.17
    POSITIVE LOGITS
    mozilla
    2.29
     Ubuntu
    2.23
     Linux
    2.22
    installed
    2.09
     servers
    2.02
    ported
    1.91
     ubuntu
    1.91
    Ubuntu
    1.90
     OS
    1.81
    Developer
    1.79
    Activations Density 0.999%

    No Known Activations