© 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. 13320
    Prev
    Next
    INDEX
    Explanations

    technical terms and structured data descriptors

    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
    53
    +0.13
    0.7%
    497
    +0.12
    0.7%
    85
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    53
    +0.13
    0.11
    438
    +0.12
    0.07
    431
    +0.12
    0.05
    Negative Logits
    .[@
    -1.76
     (>
    -1.70
     (\>
    -1.51
    istar
    -1.46
     (<
    -1.45
     (âī¥
    -1.45
    ,[@
    -1.41
    igi
    -1.36
     ArrayList
    -1.33
     costing
    -1.30
    POSITIVE LOGITS
    ³
    2.35
    ĻĤ
    2.08
    ĭ
    2.05
    º
    2.01
    Ŀ
    2.00
    ·¸
    1.96
    ·
    1.94
    ¢
    1.90
    Ķ
    1.86
    »¿
    1.83
    Activations Density 1.081%

    No Known Activations