© 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. 31225
    Prev
    Next
    INDEX
    Explanations

    references to specific standards or classifications within various contexts

    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
    198
    +0.23
    1.4%
    312
    +0.15
    0.9%
    326
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    198
    +0.23
    0.10
    312
    +0.15
    0.11
    453
    +0.14
    0.07
    Negative Logits
    Īĺ
    -2.48
    ij
    -1.90
    ply
    -1.79
    ĥ
    -1.71
    ĥ½
    -1.69
    Ĺ
    -1.64
    ?'
    -1.64
    ¾
    -1.62
    Ł
    -1.58
    ¥
    -1.58
    POSITIVE LOGITS
    ptions
    1.39
    zitter
    1.34
    Tools
    1.34
    analytic
    1.33
    agement
    1.32
     instance
    1.28
    riterion
    1.25
    \],
    1.24
    ersion
    1.21
    \](
    1.20
    Activations Density 2.307%

    No Known Activations