© 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. 31626
    Prev
    Next
    INDEX
    Explanations

    identifiers related to products and brands

    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
    +0.16
    1.0%
    170
    +0.15
    0.9%
    484
    +0.15
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    156
    +0.16
    0.39
    71
    +0.15
    0.37
    111
    +0.15
    0.34
    Negative Logits
    usterity
    -1.72
    etine
    -1.61
     violated
    -1.58
     certain
    -1.56
    aten
    -1.55
    olin
    -1.55
    Argued
    -1.47
    Ä
    -1.47
     encoding
    -1.45
    gus
    -1.45
    POSITIVE LOGITS
    ĻĤ
    2.16
    Ļª
    1.86
    ľĵ
    1.84
    ³
    1.77
    Īĺ
    1.71
    Ľ
    1.66
     yourselves
    1.55
    ounter
    1.54
    ?_
    1.52
     yourself
    1.52
    Activations Density 3.288%

    No Known Activations