© 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. 25300
    Prev
    Next
    INDEX
    Explanations

    coding snippets related to web development features or functionality

    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
    369
    +0.16
    0.9%
    365
    +0.15
    0.9%
    312
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    129
    +0.16
    0.03
    410
    +0.15
    0.13
    312
    +0.12
    0.06
    Negative Logits
    won
    -1.80
    rut
    -1.69
    okia
    -1.51
    witz
    -1.50
    anno
    -1.49
    rein
    -1.45
    volt
    -1.45
    "}](#
    -1.41
    uncher
    -1.38
    odel
    -1.38
    POSITIVE LOGITS
    Į
    3.58
    ¶
    3.07
    IJ
    3.03
    ¯
    2.97
    ©
    2.96
    ↵
    2.95
    ↵
    2.95
    2.95
    ↵↵↵
    2.95
    ↵↵
    2.95
    Activations Density 2.772%

    No Known Activations