© 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
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. Residuals
    5. 1-RES-SM
    6. 27215
    Prev
    Next
    INDEX
    Explanations

    programming-related terms specifically associated with Linux and its components

    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
    90
    +0.12
    0.7%
    191
    +0.12
    0.7%
    98
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    209
    +0.12
    0.06
    252
    +0.12
    0.04
    129
    +0.12
    0.01
    Negative Logits
     aliens
    -1.44
     apprehen
    -1.43
    rangle
    -1.42
    igens
    -1.39
    compass
    -1.38
     breath
    -1.35
     drawn
    -1.35
    tes
    -1.33
     object
    -1.33
    Recogn
    -1.33
    POSITIVE LOGITS
    BSD
    1.68
    ycin
    1.63
    bsd
    1.60
     firmware
    1.51
    ario
    1.45
     version
    1.41
     ÏĦÏīν
    1.38
    ruptcy
    1.38
    ROM
    1.37
     availability
    1.37
    Activations Density 0.677%

    No Known Activations