© 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. 4-RES-SM
    11. 12155
    Prev
    Next
    INDEX
    Explanations

    specific digit positions in numerical representations

    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/4-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.4.hook_resid_post
    Hook Layer
    4
    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
    348
    +0.19
    1.1%
    78
    +0.14
    0.9%
    30
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    348
    +0.19
    0.02
    78
    +0.14
    0.00
    9
    +0.12
    0.02
    Negative Logits
    ctic
    -1.49
    vist
    -1.37
    ground
    -1.35
    undry
    -1.26
    runner
    -1.25
     native
    -1.24
    ership
    -1.24
     closures
    -1.22
     reasons
    -1.20
     opposite
    -1.20
    POSITIVE LOGITS
    IJ
    5.03
    ¸
    4.95
    »
    4.93
    İ
    4.93
    »¿
    4.92
    ¾
    4.86
    ·
    4.84
    ¿
    4.79
    ª
    4.78
    ĵ
    4.76
    Activations Density 0.175%

    No Known Activations