© 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 EvalsExportsinterp-engineNEWAPI 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. 29634
    Prev
    Next
    INDEX
    Explanations

    terms related to electrical components and systems

    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
    +0.23
    1.3%
    201
    +0.12
    0.7%
    213
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    304
    +0.23
    0.02
    113
    +0.12
    0.02
    208
    +0.10
    0.02
    Negative Logits
     apologize
    -1.92
    ês
    -1.76
     intend
    -1.73
     vez
    -1.72
    chitz
    -1.71
    wegian
    -1.65
    ionale
    -1.59
     hers
    -1.54
    ocre
    -1.54
    ego
    -1.53
    POSITIVE LOGITS
    ¬
    3.40
    £
    3.12
    Ł
    3.04
    ¦
    2.98
    ĸ
    2.89
    Ĵ
    2.88
    ¡
    2.85
    ŀ
    2.81
    ķ
    2.75
    Ħ
    2.74
    Activations Density 0.092%

    No Known Activations