© 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. 10042
    Prev
    Next
    INDEX
    Explanations

    keywords and terminologies related to programming and data structures

    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
    +0.31
    1.9%
    369
    +0.20
    1.2%
    17
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    369
    +0.31
    0.03
    71
    +0.20
    0.17
    156
    +0.13
    0.17
    Negative Logits
    ãĤĥ
    -1.82
    ãģĴ
    -1.79
    "}](#
    -1.77
    ãģij
    -1.75
    ãĤº
    -1.73
    ãģĺ
    -1.73
    ÑĢоÑģ
    -1.71
    ãģĭ
    -1.68
    иÑĩ
    -1.68
    á½IJ
    -1.68
    POSITIVE LOGITS
     compilation
    1.35
     publ
    1.30
     conferences
    1.28
     catalogue
    1.26
     Framework
    1.23
     Assistance
    1.22
    ↵↵↵
    1.22
     consult
    1.19
    PROM
    1.19
     Monitoring
    1.19
    Activations Density 4.911%

    No Known Activations