© 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. 28852
    Prev
    Next
    INDEX
    Explanations

    references to specific research techniques or assays

    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
    445
    +0.15
    0.8%
    369
    +0.14
    0.8%
    230
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    207
    +0.15
    0.02
    445
    +0.14
    0.02
    484
    +0.13
    0.02
    Negative Logits
    etheless
    -1.67
    ferentially
    -1.61
    cibly
    -1.58
     previous
    -1.57
    theless
    -1.56
     unanimous
    -1.55
     neighbouring
    -1.54
    estly
    -1.53
    hood
    -1.53
    optera
    -1.52
    POSITIVE LOGITS
    PV
    1.98
    tawa
    1.78
    YPE
    1.72
    MP
    1.72
    imes
    1.71
    KK
    1.60
    AA
    1.59
    BF
    1.58
    Ks
    1.57
    LM
    1.55
    Activations Density 0.211%

    No Known Activations