© 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. 1-RES-SM
    11. 25170
    Prev
    Next
    INDEX
    Explanations

    references to programming languages and testing frameworks

    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/1-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.1.hook_resid_post
    Hook Layer
    1
    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
    397
    +0.19
    1.1%
    111
    +0.15
    0.9%
    173
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    73
    +0.19
    0.02
    379
    +0.15
    0.02
    345
    +0.14
    0.02
    Negative Logits
    ?’
    -1.64
     favor
    -1.63
    aneously
    -1.59
    sic
    -1.59
    opes
    -1.55
     favour
    -1.51
     due
    -1.49
    jur
    -1.49
    ...'
    -1.47
    ]{}\
    -1.45
    POSITIVE LOGITS
    ĨĴ
    3.73
    ĻĤ
    3.72
    ª
    3.43
    Ĵ
    3.42
    ¹
    3.14
    Ļª
    3.07
    ¼
    3.07
    ¢
    3.05
    3.04
    3.04
    Activations Density 0.118%

    No Known Activations