© 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 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. 10137
    Prev
    Next
    INDEX
    Explanations

    technical terms and variables related to software and coding functions

    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
    1.4%
    186
    +0.20
    1.2%
    459
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    459
    +0.23
    0.14
    354
    +0.20
    0.10
    439
    +0.13
    0.07
    Negative Logits
    °
    -2.26
    ħ
    -2.16
    ŀ
    -2.03
    Ŀ
    -2.00
    ·
    -1.97
    ¥
    -1.95
    ı
    -1.92
    İ
    -1.92
    ģ
    -1.91
    į
    -1.88
    POSITIVE LOGITS
     detected
    1.50
    ight
    1.41
    $.[]{
    1.40
    hin
    1.40
     recognise
    1.37
    FromString
    1.36
    wards
    1.33
    ).\
    1.32
     observed
    1.31
    ')
    1.31
    Activations Density 4.463%

    No Known Activations